© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123094
    Prev
    Next
    INDEX
    Explanations

    Technical questions and answers

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خل
    -0.07
     tamil
    -0.06
    ッツ
    -0.06
     FullName
    -0.06
    irket
    -0.06
     paradigm
    -0.06
     peripheral
    -0.06
     Leia
    -0.06
     USERNAME
    -0.06
    ('"
    -0.06
    POSITIVE LOGITS
     Prediction
    0.07
     *)↵↵
    0.06
     automatically
    0.06
     création
    0.06
     AppConfig
    0.06
     Resets
    0.06
    _dates
    0.06
     pest
    0.06
     cabeza
    0.06
     frantic
    0.06
    Activations Density 0.069%

    No Known Activations