© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 40486
    Prev
    Next
    INDEX
    Explanations

    Question/Answer formatting

    np_max-act · gemini-2.0-flash

    assistant-role headers and nearby chat metadata indicating the start of an assistant response in conversation-formatted text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QL
    -0.06
     Line
    -0.06
     velk
    -0.06
    EditMode
    -0.06
    ]^
    -0.06
     letz
    -0.06
     UNIQUE
    -0.06
    getResponse
    -0.06
     unpopular
    -0.06
    ел
    -0.06
    POSITIVE LOGITS
     hurdles
    0.07
    (Path
    0.06
     obscured
    0.06
    <=
    0.06
    CCC
    0.06
    시간
    0.06
    -st
    0.06
     ultrasound
    0.06
     fingers
    0.06
     JW
    0.06
    Activations Density 0.137%

    No Known Activations