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. 60549
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
    _segment
    -0.06
    _ll
    -0.06
    _fun
    -0.06
    _commands
    -0.06
     inertia
    -0.06
     与
    -0.06
     PPP
    -0.06
    Connections
    -0.06
     будь
    -0.06
     LM
    -0.06
    POSITIVE LOGITS
     keyof
    0.07
    WITHOUT
    0.07
    itled
    0.06
     #"
    0.06
    TY
    0.06
    escaping
    0.06
    logen
    0.06
    supports
    0.06
     اعتر
    0.06
     athletic
    0.06
    Activations Density 0.001%

    No Known Activations