© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 114338
    Prev
    Next
    INDEX
    Explanations

    if

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EFA
    -0.07
    _DBG
    -0.07
     retained
    -0.07
    yy
    -0.07
    _loader
    -0.07
     IMG
    -0.06
    cased
    -0.06
    .Save
    -0.06
     offensive
    -0.06
    ./
    -0.06
    POSITIVE LOGITS
    .firestore
    0.07
     xét
    0.07
     Failure
    0.07
     dictates
    0.06
    .Se
    0.06
    )].
    0.06
    .week
    0.06
    bucks
    0.06
     Δημο
    0.06
     pornost
    0.06
    Activations Density 0.517%

    No Known Activations