© 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. 90785
    Prev
    Next
    INDEX
    Explanations

    arrival

    np_max-act · gemini-2.0-flash

    intimate and suggestive scenarios involving physical attraction and sexual undertones.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily detects numeric tokens, especially floating‐point numbers with decimal values.

    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
    уса
    -0.07
     Alert
    -0.07
    (itr
    -0.07
    -db
    -0.06
     DeepCopy
    -0.06
    FETCH
    -0.06
     dieses
    -0.06
    .getNode
    -0.06
     Widgets
    -0.06
    .quest
    -0.06
    POSITIVE LOGITS
    elect
    0.07
     vt
    0.06
    MU
    0.06
     sailed
    0.06
    ンズ
    0.06
     购
    0.06
    增长
    0.06
     uomini
    0.06
    bash
    0.06
    超
    0.06
    Activations Density 0.036%

    No Known Activations