© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 22940
    Prev
    Next
    INDEX
    Explanations

    toxic

    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
     مثال
    -0.07
     P
    -0.06
    NDER
    -0.06
     kennen
    -0.06
    ="#"><
    -0.06
     DAG
    -0.06
    .'</
    -0.06
    Entries
    -0.06
     Hats
    -0.06
     pdata
    -0.06
    POSITIVE LOGITS
     Toxic
    0.10
     toxic
    0.09
     toxicity
    0.07
     Mix
    0.07
    ative
    0.07
     reflection
    0.07
    ogens
    0.07
    oxic
    0.07
    %i
    0.07
    _MULTI
    0.06
    Activations Density 0.011%

    No Known Activations