© 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. 57117
    Prev
    Next
    INDEX
    Explanations

    developments

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of “latest developments” (or similar phrases about ongoing/continued advancements).

    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
     관한
    -0.07
    егор
    -0.06
     Labor
    -0.06
    ่น
    -0.06
    oto
    -0.06
    ськ
    -0.06
    će
    -0.05
    ()!=
    -0.05
    。。↵↵
    -0.05
    -Free
    -0.05
    POSITIVE LOGITS
     developments
    0.12
     disappoint
    0.09
     langs
    0.08
    ργ
    0.08
     advancements
    0.08
    delegate
    0.07
     senator
    0.07
    navigate
    0.07
     nowadays
    0.07
    В
    0.07
    Activations Density 0.008%

    No Known Activations