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. 51587
    Prev
    Next
    INDEX
    Explanations

    Alright

    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
    ご
    -0.06
    bb
    -0.06
    gatsby
    -0.06
     dies
    -0.06
     andere
    -0.06
     ///
    -0.06
    .CONTENT
    -0.06
    }());↵
    -0.06
     cosas
    -0.06
     foresee
    -0.05
    POSITIVE LOGITS
    Alright
    0.07
     departing
    0.07
    !.
    0.06
    iment
    0.06
     alright
    0.06
    TRAN
    0.06
    FP
    0.06
    _confirm
    0.06
    ections
    0.06
    mented
    0.06
    Activations Density 0.003%

    No Known Activations