© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 105283
    Prev
    Next
    INDEX
    Explanations

    colons

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offend
    -0.07
     Haram
    -0.06
     osób
    -0.06
     шп
    -0.06
     ráp
    -0.06
     Buddy
    -0.06
     bothers
    -0.06
    cilik
    -0.06
     eldre
    -0.06
    isers
    -0.06
    POSITIVE LOGITS
    _dic
    0.07
     nun
    0.07
    。(
    0.07
    {{{
    0.07
    Leg
    0.07
    YS
    0.07
    ाल
    0.07
    _SID
    0.06
    ???
    0.06
    (ps
    0.06
    Activations Density 0.027%

    No Known Activations