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. 23-RESID-POST-AA
    6. 104209
    Prev
    Next
    INDEX
    Explanations

    Sentence punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indign
    -0.07
    .ylim
    -0.07
     pues
    -0.07
     проте
    -0.07
    ूब
    -0.06
    medi
    -0.06
     Gon
    -0.06
     авт
    -0.06
    .tools
    -0.06
     papel
    -0.06
    POSITIVE LOGITS
    .vertices
    0.07
     Calculates
    0.06
     громад
    0.06
    976
    0.06
     targetType
    0.06
     overflowing
    0.06
     pojištění
    0.06
    elig
    0.06
     tossing
    0.06
    írk
    0.06
    Activations Density 0.032%

    No Known Activations