© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109292
    Prev
    Next
    INDEX
    Explanations

    shell commands

    np_max-act · gemini-2.0-flash

    The neuron fires on the “-F” field‐separator flag in awk command lines.

    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
     celou
    -0.06
    /MM
    -0.06
     eben
    -0.06
    482
    -0.06
    =true
    -0.06
    sql
    -0.06
     boosts
    -0.06
     reduction
    -0.06
    _separator
    -0.06
     около
    -0.06
    POSITIVE LOGITS
     كن
    0.07
     сов
    0.06
    Producer
    0.06
    催
    0.06
     série
    0.06
     víde
    0.06
     quyền
    0.06
    StyleSheet
    0.06
    �
    0.06
     Carmen
    0.06
    Activations Density 0.001%

    No Known Activations