© 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. 109453
    Prev
    Next
    INDEX
    Explanations

    hyphens/slashes

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens—references, section numbers, years, page or report codes—i.e. any strings containing digits.

    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
    vinces
    -0.07
    ,X
    -0.06
     textField
    -0.06
    .Upload
    -0.06
    sortable
    -0.06
    _p
    -0.06
    UNIX
    -0.06
    .localScale
    -0.06
     FIN
    -0.06
     noch
    -0.06
    POSITIVE LOGITS
     čas
    0.07
    ($
    0.06
     équip
    0.06
     rủi
    0.06
    acebook
    0.06
    оды
    0.06
     bye
    0.06
    @Json
    0.06
    	margin
    0.06
    \[
    0.06
    Activations Density 0.004%

    No Known Activations