© 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
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 123253
    Prev
    Next
    INDEX
    Explanations

    feral animals

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _completed
    -0.06
    )();↵
    -0.06
     combust
    -0.06
     времени
    -0.06
    -quarters
    -0.06
    Explorer
    -0.06
     derin
    -0.06
     qi
    -0.06
    _barrier
    -0.06
     خدا
    -0.06
    POSITIVE LOGITS
     motel
    0.08
    ersonic
    0.08
    (coder
    0.07
    lum
    0.07
    aban
    0.07
    �
    0.07
    ρες
    0.06
    _ALIGNMENT
    0.06
     implic
    0.06
    STER
    0.06
    Activations Density 0.006%

    No Known Activations