© 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. 18405
    Prev
    Next
    INDEX
    Explanations

    police reports

    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_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
    etxt
    -0.07
    \xd
    -0.07
     dav
    -0.07
    _Cl
    -0.06
    night
    -0.06
     acoustic
    -0.06
     cit
    -0.06
     poor
    -0.06
    Poor
    -0.06
     Hussein
    -0.06
    POSITIVE LOGITS
     Tòa
    0.07
    แบ
    0.06
     відб
    0.06
     मह
    0.06
    ailable
    0.06
    ENCIES
    0.06
    limits
    0.06
    --*/↵
    0.06
     Vatican
    0.06
     ně
    0.06
    Activations Density 0.022%

    No Known Activations