© 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. 23-RESID-POST-AA
    11. 30188
    Prev
    Next
    INDEX
    Explanations

    legal defenses and arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acad
    -0.06
    target
    -0.06
    セ
    -0.06
     Creating
    -0.06
    ollower
    -0.06
    _get
    -0.06
     In
    -0.06
    ']>
    -0.06
     @}
    -0.06
    iffs
    -0.06
    POSITIVE LOGITS
    .nickname
    0.07
    findOrFail
    0.07
     �
    0.07
     Northwestern
    0.06
     Dietary
    0.06
    �
    0.06
     BK
    0.06
     defended
    0.06
     何
    0.06
    たし
    0.06
    Activations Density 0.004%

    No Known Activations