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. 108900
    Prev
    Next
    INDEX
    Explanations

    Code with variable i

    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
    CON
    -0.07
     cp
    -0.07
     -*
    -0.07
    con
    -0.06
    γεν
    -0.06
     hardness
    -0.06
    MW
    -0.06
     않고
    -0.06
    combine
    -0.06
     '^
    -0.06
    POSITIVE LOGITS
    -wsj
    0.08
     매
    0.07
    ологии
    0.07
    ertime
    0.07
    ControlItem
    0.06
     μέσα
    0.06
    ními
    0.06
    (pkt
    0.06
     FontAwesome
    0.06
     vá
    0.06
    Activations Density 0.047%

    No Known Activations