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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 104389
    Prev
    Next
    INDEX
    Explanations

    who

    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
    _star
    -0.06
     ambassador
    -0.06
    вати
    -0.06
     baths
    -0.06
     milit
    -0.06
    INK
    -0.06
     μα
    -0.06
    propri
    -0.06
     mounts
    -0.06
     mount
    -0.06
    POSITIVE LOGITS
    (':',
    0.07
     RR
    0.07
    )。
    0.07
     αυ
    0.07
    )\
    0.07
     людей
    0.07
    _METADATA
    0.06
    errated
    0.06
    SCRIPTOR
    0.06
    ẩu
    0.06
    Activations Density 0.051%

    No Known Activations