© 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. 91970
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens representing metrics or counts (e.g. follower/view numbers, percentages).

    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
     Solo
    -0.06
    bane
    -0.06
    .Platform
    -0.06
     thấp
    -0.06
     Preferences
    -0.06
    welcome
    -0.06
    jectories
    -0.06
    (phone
    -0.06
     hedge
    -0.06
    .destroy
    -0.05
    POSITIVE LOGITS
    ΕΛ
    0.08
    失
    0.07
    liğinin
    0.07
    ัจจ
    0.07
    [dim
    0.06
    arbon
    0.06
     Inv
    0.06
    Teachers
    0.06
    :ｉ
    0.06
    کری
    0.06
    Activations Density 0.027%

    No Known Activations