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. 75397
    Prev
    Next
    INDEX
    Explanations

    law

    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
    活
    -0.07
    _exact
    -0.06
     】
    -0.06
     rivalry
    -0.06
     размещ
    -0.06
     تشکیل
    -0.06
    tah
    -0.06
    _than
    -0.06
     원
    -0.06
     annoyed
    -0.06
    POSITIVE LOGITS
    лерг
    0.08
    licate
    0.07
    .nav
    0.07
    /action
    0.07
    aqu
    0.07
    」,
    0.06
    ми
    0.06
    ",$
    0.06
    лини
    0.06
     мом
    0.06
    Activations Density 0.002%

    No Known Activations