© 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. 7-RESID-POST-AA
    6. 108375
    Prev
    Next
    INDEX
    Explanations

    it

    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
     %%
    -0.07
    /new
    -0.07
     Penny
    -0.07
    icago
    -0.07
    histor
    -0.07
    means
    -0.07
     مما
    -0.06
    Sw
    -0.06
    —in
    -0.06
     backups
    -0.06
    POSITIVE LOGITS
     noh
    0.06
    ât
    0.06
    setData
    0.06
    BindingUtil
    0.06
    Spirit
    0.06
     Compet
    0.06
    puted
    0.06
     gunshot
    0.06
    TAIL
    0.06
     funk
    0.06
    Activations Density 0.001%

    No Known Activations