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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 94457
    Prev
    Next
    INDEX
    Explanations

    Asking for help

    np_max-act · gemini-2.0-flash

    Instances where the text is asking for help or requesting assistance (help/need-style requests).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    :right
    -0.09
    species
    -0.07
     ABOVE
    -0.07
     fluorescent
    -0.06
     Hyundai
    -0.06
     timestamp
    -0.06
     bố
    -0.06
     Bên
    -0.06
     paralyzed
    -0.06
    Properties
    -0.06
    POSITIVE LOGITS
     rám
    0.07
     Lump
    0.06
    STRU
    0.06
    .Hosting
    0.06
    喜
    0.06
    าคม
    0.06
    异
    0.06
    �
    0.06
     land
    0.06
    robat
    0.06
    Activations Density 0.161%

    No Known Activations