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. 19-RESID-POST-AA
    6. 83431
    Prev
    Next
    INDEX
    Explanations

    intubation

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sir
    -0.07
    north
    -0.07
    uve
    -0.06
     Silence
    -0.06
     модель
    -0.06
    _INTR
    -0.06
    -api
    -0.06
    郎
    -0.06
    Mah
    -0.06
     aiming
    -0.06
    POSITIVE LOGITS
     controle
    0.07
    _fee
    0.07
     neu
    0.06
    [type
    0.06
    _AST
    0.06
    CppTypeDefinition
    0.06
     Hemisphere
    0.06
    φό
    0.06
    pad
    0.06
    (TAG
    0.06
    Activations Density 0.015%

    No Known Activations