© 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. 68870
    Prev
    Next
    INDEX
    Explanations

    scientific software/tools

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of specific software or algorithm/tool names (e.g. “Platanus,” “assemblers,” “tools,” “BUSCO,” etc.) in method descriptions.

    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
    Virgin
    -0.07
    Hotel
    -0.06
    Informe
    -0.06
    Fac
    -0.06
     imap
    -0.06
    ุมชน
    -0.06
    ////////////////////////////////////////////////////////////////////////
    -0.06
    �
    -0.06
     Вели
    -0.06
    dız
    -0.06
    POSITIVE LOGITS
    -wrap
    0.07
     Woche
    0.07
    bench
    0.06
     cree
    0.06
     Monroe
    0.06
     Wonderful
    0.06
    ريد
    0.06
     jud
    0.06
    won
    0.06
    due
    0.06
    Activations Density 0.016%

    No Known Activations