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. 11-RESID-POST-AA
    6. 22105
    Prev
    Next
    INDEX
    Explanations

    androgens

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     أل
    -0.07
     徒
    -0.07
     '*'
    -0.06
     тим
    -0.06
    .Bit
    -0.06
    清
    -0.06
    .Table
    -0.06
     Jensen
    -0.06
     \%
    -0.06
     tích
    -0.06
    POSITIVE LOGITS
    aname
    0.07
     října
    0.06
    VK
    0.06
    Enums
    0.06
    dance
    0.06
     scipy
    0.06
     ]↵↵
    0.06
    ูร
    0.06
    ect
    0.06
    rschein
    0.06
    Activations Density 0.499%

    No Known Activations