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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30390
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on the single‐letter receiver identifiers in Go method signatures (e.g. the “p” or “c” in “func (p *Products) List…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    elements related to file handling in a programming context.

    oai_token-act-pair · gpt-4o-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
     VERSION
    -0.07
     مش
    -0.07
    amine
    -0.07
     απ
    -0.06
    chw
    -0.06
    (sock
    -0.06
    (in
    -0.06
    'We
    -0.06
    726
    -0.06
    Forge
    -0.06
    POSITIVE LOGITS
     Christianity
    0.07
    instrument
    0.07
     сто
    0.06
     Turkish
    0.06
    جمة
    0.06
    Uber
    0.06
    lemma
    0.06
     исследования
    0.06
    indow
    0.06
    irlines
    0.06
    Activations Density 0.003%

    No Known Activations