© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38025
    Prev
    Next
    INDEX
    Explanations

    future events

    np_max-act · gemini-2.0-flash

    keywords related to events and announcements in public settings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to language announcing or promoting upcoming events—especially future‐tense/imperative cues like “will,” “join,” “during,” “presenting,” or “screen.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avengers
    -0.07
    const
    -0.07
     vlan
    -0.06
     liver
    -0.06
    .CLASS
    -0.06
    vron
    -0.06
    _bottom
    -0.06
     polish
    -0.06
     slander
    -0.06
     tracked
    -0.06
    POSITIVE LOGITS
     अगर
    0.06
    vůli
    0.06
     coz
    0.06
     defenses
    0.06
     bazı
    0.06
     fq
    0.06
     Translation
    0.06
     formats
    0.06
    [jj
    0.06
     kein
    0.06
    Activations Density 0.047%

    No Known Activations