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. 53221
    Prev
    Next
    INDEX
    Explanations

    sports penalties

    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
     increased
    -0.07
     рис
    -0.07
    =(
    -0.06
    TestingModule
    -0.06
    _handler
    -0.06
     continua
    -0.06
    continue
    -0.06
    то
    -0.06
    ``,
    -0.06
    ,o
    -0.06
    POSITIVE LOGITS
    екси
    0.07
    Ev
    0.07
     Beta
    0.06
    	document
    0.06
     urlString
    0.06
    .!
    0.06
    arger
    0.06
     celebrates
    0.06
    ina
    0.06
     tier
    0.06
    Activations Density 0.019%

    No Known Activations