Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84366
    Prev
    Next
    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the “static” storage‐class specifier in C code.

    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
    _alloc
    -0.07
    _support
    -0.07
    Tim
    -0.06
     tot
    -0.06
    _file
    -0.06
    _itr
    -0.06
    .safe
    -0.06
    .uk
    -0.06
    Exp
    -0.06
    _PWR
    -0.06
    POSITIVE LOGITS
    .GONE
    0.07
    vic
    0.06
     Camel
    0.06
     نس
    0.06
    並
    0.06
    ’an
    0.06
     января
    0.06
     داشت
    0.06
    'an
    0.06
    rey
    0.06
    Activations Density 0.032%

    No Known Activations