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. 29049
    Prev
    Next
    INDEX
    Explanations

    sole

    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
    ::::::
    -0.07
     hay
    -0.07
    ificado
    -0.07
    lararası
    -0.07
     insect
    -0.06
     kriz
    -0.06
     geçir
    -0.06
    ..."
    -0.06
    rawl
    -0.06
     Cr
    -0.06
    POSITIVE LOGITS
     solely
    0.08
     Sole
    0.08
     sole
    0.07
    _strdup
    0.07
     поє
    0.07
     CString
    0.07
     Society
    0.06
    μέ
    0.06
     torpedo
    0.06
    .Submit
    0.06
    Activations Density 0.006%

    No Known Activations