Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 128996
    Prev
    Next
    INDEX
    Explanations

    gain

    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
    brick
    -0.07
     postal
    -0.07
    uez
    -0.07
     Truck
    -0.06
    .txt
    -0.06
    Deck
    -0.06
    .voice
    -0.06
    ubuntu
    -0.06
                                                                           
    -0.06
    ック
    -0.06
    POSITIVE LOGITS
     gains
    0.16
     gain
    0.15
     Gain
    0.14
    Gain
    0.10
     gained
    0.09
    gain
    0.08
     gaining
    0.08
    Win
    0.08
    _gain
    0.08
     Gaines
    0.07
    Activations Density 0.007%

    No Known Activations