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. 27-RESID-POST-AA
    6. 10592
    Prev
    Next
    INDEX
    Explanations

    public consciousness

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ********************
    -0.07
     cycl
    -0.06
     franchises
    -0.06
    _SMS
    -0.06
     professions
    -0.06
    Accessible
    -0.06
    Ан
    -0.06
    <Block
    -0.06
    举
    -0.06
    Dialogue
    -0.06
    POSITIVE LOGITS
     cal
    0.07
     Degrees
    0.07
     Croatian
    0.06
    rades
    0.06
    рії
    0.06
     thwart
    0.06
     dumpster
    0.06
    kker
    0.06
     lunch
    0.06
    aż
    0.06
    Activations Density 0.063%

    No Known Activations