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. 109795
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     관리
    -0.07
     cinematic
    -0.07
     رسانه
    -0.07
    _policy
    -0.07
     省
    -0.07
     itch
    -0.06
     ay
    -0.06
     MPS
    -0.06
    accept
    -0.06
     heads
    -0.06
    POSITIVE LOGITS
    یدا
    0.07
    زم
    0.06
    ]bool
    0.06
     widened
    0.06
     AUG
    0.06
    曼
    0.06
    대로
    0.06
    _NB
    0.06
    quo
    0.06
    ума
    0.06
    Activations Density 0.163%

    No Known Activations