© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 93598
    Prev
    Next
    INDEX
    Explanations

    -id

    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
    at
    -0.06
    堡
    -0.06
     ^.
    -0.06
    )=>
    -0.06
    _tw
    -0.06
     assum
    -0.06
    article
    -0.06
    _behavior
    -0.06
    functional
    -0.06
    Southern
    -0.06
    POSITIVE LOGITS
    -id
    0.25
    -ID
    0.10
    아서
    0.08
    fid
    0.07
     UserId
    0.07
    idar
    0.07
    /id
    0.07
    ुरक
    0.07
    лож
    0.07
     glEnd
    0.06
    Activations Density 0.001%

    No Known Activations