© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 628
    Prev
    Next
    INDEX
    Explanations

    fopen

    np_max-act · gemini-2.0-flash

    The neuron fires on C file‐I/O API calls (e.g. fopen, fseek, fclose).

    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
     trả
    -0.08
     withheld
    -0.07
    /rem
    -0.06
     المت
    -0.06
    trail
    -0.06
    enef
    -0.06
    Comm
    -0.06
     commenting
    -0.06
     commentaire
    -0.06
    .persist
    -0.06
    POSITIVE LOGITS
    =fopen
    0.08
     fopen
    0.08
    iệc
    0.06
     vợ
    0.06
    _NET
    0.06
    ,t
    0.06
    orio
    0.06
    -dot
    0.06
    غال
    0.06
    アル
    0.06
    Activations Density 0.001%

    No Known Activations