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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 46168
    Prev
    Next
    INDEX
    Explanations

    sports teams and numbers

    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
     مطالعه
    -0.07
     така
    -0.06
     roli
    -0.06
     ebx
    -0.06
     Examples
    -0.06
     칼
    -0.06
    ifique
    -0.06
     ye
    -0.06
     awakened
    -0.06
    buch
    -0.06
    POSITIVE LOGITS
     equipment
    0.06
    -graph
    0.06
     invasion
    0.06
     outage
    0.06
     vans
    0.06
    -aut
    0.06
     mpl
    0.06
     frustration
    0.06
     kunnen
    0.06
    ."',
    0.06
    Activations Density 0.005%

    No Known Activations