© 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
    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. 1869
    Prev
    Next
    INDEX
    Explanations

    this

    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
    sse
    -0.06
     depths
    -0.06
     गई
    -0.06
    trap
    -0.06
     Carmen
    -0.06
    trait
    -0.06
    awn
    -0.06
    licher
    -0.06
    Mapper
    -0.06
     преж
    -0.06
    POSITIVE LOGITS
    (Vector
    0.07
    _FILENO
    0.07
     mism
    0.07
    يط
    0.07
     neoliberal
    0.07
     colossal
    0.06
     IST
    0.06
    �名
    0.06
     elit
    0.06
     portraying
    0.06
    Activations Density 0.086%

    No Known Activations