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. 19-RESID-POST-AA
    6. 57218
    Prev
    Next
    INDEX
    Explanations

    @

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瓜
    -0.07
    .Localization
    -0.07
    (cb
    -0.07
     пти
    -0.06
     Bea
    -0.06
    .lua
    -0.06
     constraints
    -0.06
     pulmonary
    -0.06
    into
    -0.06
     elles
    -0.06
    POSITIVE LOGITS
     Ledger
    0.06
     Played
    0.06
    -reaching
    0.06
     earthqu
    0.06
     Viet
    0.06
    lád
    0.06
     Legion
    0.06
    !(:
    0.06
     Registr
    0.06
    material
    0.05
    Activations Density 0.008%

    No Known Activations