© 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. 109627
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    references to specific agreements or contracts and associated parties involved in discussions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on expressions of ability or possibility, particularly on occurrences of “able to ….”.

    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
    -fiction
    -0.07
     RSVP
    -0.06
    ítulo
    -0.06
     страниц
    -0.06
     latina
    -0.06
    Pic
    -0.06
     vou
    -0.06
     AST
    -0.06
    374
    -0.06
    _restrict
    -0.06
    POSITIVE LOGITS
    _CHARACTER
    0.08
    ."'";↵
    0.07
     Billing
    0.07
    SuppressWarnings
    0.07
    よび
    0.06
    	lua
    0.06
    (HttpServletRequest
    0.06
     ICommand
    0.06
     多
    0.06
    \",\"
    0.06
    Activations Density 0.001%

    No Known Activations