© 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. 10887
    Prev
    Next
    INDEX
    Explanations

    füh

    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
    handleChange
    -0.07
    假
    -0.07
    ark
    -0.06
    arks
    -0.06
    dob
    -0.06
    ART
    -0.06
    λικά
    -0.06
    acc
    -0.06
     cameo
    -0.06
    $text
    -0.06
    POSITIVE LOGITS
    umlu
    0.07
    ungs
    0.07
    ebilir
    0.07
    führ
    0.07
    Archivo
    0.07
    EF
    0.07
    .setSelection
    0.07
    .Footer
    0.07
    過
    0.07
    통령
    0.07
    Activations Density 0.004%

    No Known Activations