© 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. 15-RESID-POST-AA
    11. 125096
    Prev
    Next
    INDEX
    Explanations

    .ylabel

    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
    Matcher
    -0.07
     biến
    -0.07
     쓰
    -0.07
     gx
    -0.07
    stud
    -0.06
     builtin
    -0.06
     باز
    -0.06
    ToInt
    -0.06
     cazzo
    -0.06
     광
    -0.06
    POSITIVE LOGITS
    _bridge
    0.07
     prav
    0.07
    pun
    0.06
    .Down
    0.06
    loadModel
    0.06
    .xlabel
    0.06
    (outfile
    0.06
    .dropdown
    0.06
    (kernel
    0.06
     Universidad
    0.06
    Activations Density 0.003%

    No Known Activations