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. 108479
    Prev
    Next
    INDEX
    Explanations

    hazard

    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
    (com
    -0.07
    embrance
    -0.07
    onymous
    -0.07
     acquaintance
    -0.07
     #+#
    -0.06
    Atlantic
    -0.06
    ]<<"
    -0.06
     Language
    -0.06
    //----------------------------------------------------------------
    -0.06
     огранич
    -0.06
    POSITIVE LOGITS
     hazards
    0.10
     Hazard
    0.09
     hazard
    0.09
     hazardous
    0.09
    _MAT
    0.07
    azard
    0.07
     onError
    0.07
    .spec
    0.06
    sealed
    0.06
    bestos
    0.06
    Activations Density 0.005%

    No Known Activations