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. 3-RESID-POST-AA
    6. 122818
    Prev
    Next
    INDEX
    Explanations

    arc

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    빌
    -0.07
     shampoo
    -0.07
    phoneNumber
    -0.06
     Julia
    -0.06
    jit
    -0.06
    (cap
    -0.06
    Chef
    -0.06
    bí
    -0.06
     requestData
    -0.06
    grpc
    -0.06
    POSITIVE LOGITS
     arc
    0.26
     Arc
    0.19
     arcs
    0.17
    Arc
    0.15
    _arc
    0.09
     Merk
    0.08
     ARC
    0.08
    (arc
    0.07
     ark
    0.07
     posit
    0.07
    Activations Density 0.003%

    No Known Activations