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. 100487
    Prev
    Next
    INDEX
    Explanations

    prosthetics

    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
    ABCDEFG
    -0.06
     zaměst
    -0.06
    finished
    -0.06
     Cannabis
    -0.06
     horr
    -0.06
    =read
    -0.06
     طبق
    -0.06
    े।
    -0.06
    ala
    -0.06
    _workers
    -0.06
    POSITIVE LOGITS
    oky
    0.07
     Ã
    0.06
    072
    0.06
    .GL
    0.06
     sym
    0.06
     Î
    0.06
    덤프
    0.06
    /public
    0.06
     cert
    0.06
    oint
    0.06
    Activations Density 0.006%

    No Known Activations