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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125215
    Prev
    Next
    INDEX
    Explanations

    About

    np_max-act · gemini-2.0-flash

    references to historical or geographical subjects.

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

    This neuron detects numeric tokens—especially decimal values or measurements—in the text.

    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
    що
    -0.07
     []
    -0.07
    ópez
    -0.06
     pointed
    -0.06
     handheld
    -0.06
    offee
    -0.06
    -i
    -0.06
    755
    -0.06
    _mount
    -0.06
     signaling
    -0.06
    POSITIVE LOGITS
     svens
    0.07
     место
    0.07
    ()):↵
    0.07
     Scha
    0.07
    _nth
    0.07
    íš
    0.06
     voll
    0.06
     aus
    0.06
    )};↵
    0.06
     testimon
    0.06
    Activations Density 0.025%

    No Known Activations