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. 85780
    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_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
     appliances
    -0.07
     Wan
    -0.07
     Milton
    -0.07
     bourgeois
    -0.07
     Bracket
    -0.06
     radiant
    -0.06
    ังจาก
    -0.06
     Zahl
    -0.06
     ness
    -0.06
     coral
    -0.06
    POSITIVE LOGITS
     §§
    0.08
    (hdc
    0.06
     (*.
    0.06
    )((
    0.06
    ↵    ↵    ↵
    0.06
    clarsimp
    0.06
    }↵↵↵
    0.06
    ","",
    0.06
    しており
    0.06
    '],$_
    0.06
    Activations Density 0.001%

    No Known Activations