© 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. 3-RESID-POST-AA
    11. 94089
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <Pair
    -0.06
    .school
    -0.06
     admit
    -0.06
    dense
    -0.06
    .render
    -0.06
     Maced
    -0.06
    _tooltip
    -0.06
     Rak
    -0.06
    /icon
    -0.06
    internal
    -0.05
    POSITIVE LOGITS
    _traffic
    0.07
    vání
    0.07
    <&
    0.07
     pública
    0.07
    اعي
    0.06
    ided
    0.06
     verb
    0.06
    久
    0.06
     درس
    0.06
     diret
    0.06
    Activations Density 0.009%

    No Known Activations