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. 7-RESID-POST-AA
    6. 93265
    Prev
    Next
    INDEX
    Explanations

    engine

    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_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
     CRC
    -0.07
    _VAR
    -0.07
     tat
    -0.07
    foobar
    -0.06
     Parish
    -0.06
    CRC
    -0.06
     placement
    -0.06
    AR
    -0.06
    .Marshal
    -0.06
     rar
    -0.06
    POSITIVE LOGITS
     engine
    0.19
     Engine
    0.17
    Engine
    0.16
    engine
    0.15
     Engines
    0.15
     engines
    0.14
    .engine
    0.14
    _engine
    0.11
    .Engine
    0.10
    	engine
    0.10
    Activations Density 0.013%

    No Known Activations