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. 95105
    Prev
    Next
    INDEX
    Explanations

    expenses

    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
    _corpus
    -0.07
    раста
    -0.07
    _contr
    -0.06
     dados
    -0.06
    reiben
    -0.06
     wurden
    -0.06
     눈을
    -0.06
    accion
    -0.06
     kimse
    -0.06
    +v
    -0.06
    POSITIVE LOGITS
     spooky
    0.07
    ->{'
    0.07
     суще
    0.07
     독
    0.06
     �
    0.06
    'value
    0.06
    .black
    0.06
     regex
    0.06
     callback
    0.06
     struggled
    0.06
    Activations Density 0.000%

    No Known Activations