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. 10657
    Prev
    Next
    INDEX
    Explanations

    punctuation and "but"

    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
    ują
    -0.07
     임
    -0.06
    申
    -0.06
    ンの
    -0.06
     radio
    -0.06
    lobber
    -0.06
    kır
    -0.06
     χρόνια
    -0.06
     akıl
    -0.06
     Smy
    -0.06
    POSITIVE LOGITS
    .direct
    0.07
    (marker
    0.07
     aperture
    0.07
     complaining
    0.07
     requires
    0.07
     something
    0.06
    ,与
    0.06
    ह
    0.06
    _marshaled
    0.06
    .Agent
    0.06
    Activations Density 0.165%

    No Known Activations