© 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. 88906
    Prev
    Next
    INDEX
    Explanations

    another

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and figures, identifying occurrences of numbers and measurements in the 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
     ID
    -0.09
    .Set
    -0.08
    ID
    -0.08
    PI
    -0.08
    in
    -0.07
     Level
    -0.07
    .Site
    -0.07
    itime
    -0.07
     Rt
    -0.07
     CPS
    -0.07
    POSITIVE LOGITS
     another
    0.20
     Another
    0.16
    another
    0.16
    Another
    0.15
     An
    0.08
    An
    0.08
    いて
    0.08
     otro
    0.08
     a
    0.08
    >An
    0.08
    Activations Density 0.031%

    No Known Activations