© 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. 11-RESID-POST-AA
    11. 89812
    Prev
    Next
    INDEX
    Explanations

    highlight

    np_max-act · gemini-2.0-flash

    This neuron specifically detects decimal‐formatted numbers (tokens containing a period, e.g., “3.1679”).

    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
     recursion
    -0.09
    ()['
    -0.07
     arteries
    -0.07
     Đào
    -0.06
     Moo
    -0.06
     computes
    -0.06
     resemblance
    -0.06
     College
    -0.06
     conceived
    -0.06
    ()=="
    -0.06
    POSITIVE LOGITS
     highlight
    0.14
     highlights
    0.13
     highlighted
    0.13
     highlighting
    0.11
    Highlights
    0.10
     Highlight
    0.10
    highlight
    0.09
     Highlights
    0.09
    Highlight
    0.08
    Highlighted
    0.08
    Activations Density 0.010%

    No Known Activations