© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25999
    Prev
    Next
    INDEX
    Explanations

    oral

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maman
    -0.07
     Gene
    -0.07
    .snp
    -0.07
     функци
    -0.07
    .rdf
    -0.06
     Diane
    -0.06
     Cre
    -0.06
     SVM
    -0.06
    (exception
    -0.06
     Gomez
    -0.06
    POSITIVE LOGITS
     Electoral
    0.11
     electoral
    0.11
    Postal
    0.09
    odal
    0.08
    stral
    0.08
    provider
    0.07
    Apollo
    0.07
     postal
    0.07
     lottery
    0.07
     imperfect
    0.07
    Activations Density 0.001%

    No Known Activations