© 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. 7-RESID-POST-AA
    11. 53689
    Prev
    Next
    INDEX
    Explanations

    Swallowing and choking hazards

    np_max-act · gemini-2.0-flash

    mentions of safety hazards involving ingestion, choking, or suffocation, especially warnings about small parts and toy safety for children and pets.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redistributed
    -0.08
    652
    -0.08
     Tort
    -0.07
    usch
    -0.07
    grade
    -0.07
     Dodge
    -0.07
    262
    -0.07
    يل
    -0.07
     باب
    -0.06
     companions
    -0.06
    POSITIVE LOGITS
     comentarios
    0.06
    -dr
    0.06
     bekom
    0.06
    nonnull
    0.06
     salesman
    0.06
     dostan
    0.06
    EDITOR
    0.06
    licative
    0.06
     acompañ
    0.06
    şiv
    0.06
    Activations Density 0.027%

    No Known Activations