© 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. 90746
    Prev
    Next
    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash

    This neuron detects the “->” arrow token used in code snippets (e.g. for option assignments or mappings).

    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
    ich
    -0.09
    h
    -0.08
    ith
    -0.08
    ห
    -0.08
    House
    -0.07
    veh
    -0.07
    SH
    -0.07
    ah
    -0.07
    sh
    -0.07
    _high
    -0.07
    POSITIVE LOGITS
     ->
    0.09
    užel
    0.09
    ↓
    0.08
     ↔
    0.08
     Ventura
    0.07
    →
    0.07
     →
    0.07
     cevap
    0.07
     EVT
    0.07
     -(
    0.07
    Activations Density 0.015%

    No Known Activations