© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 35089
    Prev
    Next
    INDEX
    Explanations

    code scripting

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _called
    -0.07
    _SN
    -0.07
    孤
    -0.07
    :D
    -0.07
     complications
    -0.07
     관한
    -0.06
    Но
    -0.06
     vnode
    -0.06
    .TH
    -0.06
     organised
    -0.06
    POSITIVE LOGITS
    kům
    0.07
    (jq
    0.07
    쪽
    0.07
    ACEMENT
    0.06
    stub
    0.06
    SCRIPT
    0.06
     Powerful
    0.06
     Rand
    0.06
    ilk
    0.06
     Lomb
    0.06
    Activations Density 0.043%

    No Known Activations