© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42550
    Prev
    Next
    INDEX
    Explanations

    past tense/events

    np_max-act · gemini-2.0-flash

    This neuron activates on French-language words (including French-specific accents and vocabulary).

    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
    "description
    -0.08
     transporter
    -0.07
    svn
    -0.07
     resurrect
    -0.06
    ="\
    -0.06
    _pairs
    -0.06
     برخورد
    -0.06
    Exactly
    -0.06
     سمت
    -0.06
    	light
    -0.06
    POSITIVE LOGITS
    binations
    0.07
    plements
    0.07
     kvinde
    0.06
     năng
    0.06
     sensational
    0.06
    AsyncResult
    0.06
    genes
    0.06
     Symptoms
    0.06
     speculated
    0.06
    OptionsItemSelected
    0.06
    Activations Density 0.119%

    No Known Activations