© 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. 15-RESID-POST-AA
    6. 85220
    Prev
    Next
    INDEX
    Explanations

    represent

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _CLEAN
    -0.07
    ůl
    -0.07
     flaw
    -0.07
    Cool
    -0.06
    _ll
    -0.06
     issuance
    -0.06
     effort
    -0.06
     issuing
    -0.06
    oco
    -0.06
    _cc
    -0.06
    POSITIVE LOGITS
     represented
    0.11
     represent
    0.10
     representation
    0.09
     Represent
    0.09
    represent
    0.09
     representing
    0.09
     represents
    0.08
    代表
    0.08
    repr
    0.08
     representations
    0.08
    Activations Density 0.034%

    No Known Activations