© 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. 126838
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals containing decimal points (floating‐point numbers).

    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
     enriched
    -0.07
    Industry
    -0.07
    Rect
    -0.06
     >>
    -0.06
     mirror
    -0.06
    FINITY
    -0.06
     cinema
    -0.06
     ruined
    -0.06
     centre
    -0.06
     service
    -0.06
    POSITIVE LOGITS
    ูด
    0.08
     rõ
    0.07
    Take
    0.06
     TAKE
    0.06
    :".
    0.06
    .land
    0.06
     pravidel
    0.06
    rač
    0.06
     Prostitutas
    0.06
    /local
    0.06
    Activations Density 0.012%

    No Known Activations