Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 10479
    Prev
    Next
    INDEX
    Explanations

    Continue

    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
     manuscripts
    -0.07
     reactions
    -0.06
    Tan
    -0.06
    //
    -0.06
    ))));↵
    -0.06
     Formation
    -0.06
     }];↵
    -0.06
     lâu
    -0.06
    ्र
    -0.06
    //@
    -0.06
    POSITIVE LOGITS
    ество
    0.07
     redistribute
    0.07
     Refresh
    0.06
    _PHP
    0.06
     numberOf
    0.06
     oy
    0.06
    ACHI
    0.06
     sandwich
    0.06
     Charl
    0.06
     Ellie
    0.06
    Activations Density 0.002%

    No Known Activations