© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30624
    Prev
    Next
    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal‐formatted numeric values (e.g. averages, measures, statistics) in the scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    منی
    -0.07
    (mapStateToProps
    -0.06
    ันยายน
    -0.06
    aws
    -0.06
    ذار
    -0.06
    赵
    -0.06
    Stroke
    -0.06
    .Paint
    -0.06
    관계
    -0.06
     мінім
    -0.05
    POSITIVE LOGITS
    "?↵↵
    0.08
    ero
    0.07
    тю
    0.07
     SIZE
    0.07
     dolls
    0.07
     verb
    0.07
     reasoning
    0.07
     inverse
    0.07
     sir
    0.06
     dig
    0.06
    Activations Density 0.008%

    No Known Activations