© 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. 73709
    Prev
    Next
    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens representing floating‐point values (decimal 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
    TypeID
    -0.07
    /swagger
    -0.07
     butterknife
    -0.06
     feedback
    -0.06
    FTWARE
    -0.06
    "][$
    -0.06
    \Base
    -0.06
    -quality
    -0.06
     Kurdistan
    -0.06
    هور
    -0.06
    POSITIVE LOGITS
     reiterated
    0.08
     themselves
    0.07
    optim
    0.06
     <>↵
    0.06
    ZR
    0.06
    Qi
    0.06
     HIS
    0.06
    いで
    0.06
    是
    0.06
    positive
    0.06
    Activations Density 0.056%

    No Known Activations