© 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. 110206
    Prev
    Next
    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on numeric measurement values and scale definitions (e.g. “0 = no visible signal; 3 = optimal signal”) and similar quantitative/statistical figures.

    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
     Himself
    -0.08
     noted
    -0.07
     themselves
    -0.06
     Cod
    -0.06
     coastal
    -0.06
     Bucket
    -0.06
     counted
    -0.06
     himself
    -0.06
    characters
    -0.06
     Recruitment
    -0.06
    POSITIVE LOGITS
    MMC
    0.07
     đô
    0.07
    indx
    0.06
    !=(
    0.06
    ไว
    0.06
    amage
    0.06
    ombie
    0.06
    oha
    0.06
     showroom
    0.06
    には
    0.06
    Activations Density 0.016%

    No Known Activations