© 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. 19-RESID-POST-AA
    11. 57829
    Prev
    Next
    INDEX
    Explanations

    Cambridge

    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
     Dol
    -0.07
     Austin
    -0.06
     vowed
    -0.06
    Ngoài
    -0.06
    \Traits
    -0.06
    っき
    -0.06
     hookers
    -0.06
     Ngoài
    -0.06
     StringField
    -0.06
    79
    -0.06
    POSITIVE LOGITS
     Cambridge
    0.11
    emachine
    0.07
     Jose
    0.07
     allowances
    0.07
    training
    0.07
    xford
    0.07
    amed
    0.07
    _dash
    0.07
    geist
    0.07
     Zurich
    0.07
    Activations Density 0.002%

    No Known Activations