© 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. 3-RESID-POST-AA
    11. 123147
    Prev
    Next
    INDEX
    Explanations

    _output

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Does
    -0.06
    __).
    -0.06
    (paren
    -0.06
     MPH
    -0.06
     Sidney
    -0.06
     отнош
    -0.06
    ."</
    -0.06
    ️
    -0.06
    ského
    -0.06
    .getOwnPropertyDescriptor
    -0.06
    POSITIVE LOGITS
    _output
    0.25
    .ExecuteReader
    0.08
     getMenuInflater
    0.07
    ussen
    0.07
     voted
    0.07
    \HttpFoundation
    0.06
     Між
    0.06
    _OUTPUT
    0.06
     Bethlehem
    0.06
    ॉस
    0.06
    Activations Density 0.002%

    No Known Activations