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. 15-RESID-POST-AA
    6. 114601
    Prev
    Next
    INDEX
    Explanations

    leaked

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :".
    -0.06
     Ding
    -0.06
    _LIGHT
    -0.06
     ranch
    -0.06
     Lynn
    -0.06
    wend
    -0.06
    _clip
    -0.06
     prevention
    -0.06
    μ
    -0.06
     marshal
    -0.06
    POSITIVE LOGITS
     _↵
    0.07
     Winnipeg
    0.07
     fax
    0.06
     NHL
    0.06
     tại
    0.06
     affinity
    0.06
    uegos
    0.06
    emap
    0.06
    ')↵↵↵↵
    0.06
     Msg
    0.06
    Activations Density 0.000%

    No Known Activations