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

    Neuronpedia

    APICircuit 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. 86319
    Prev
    Next
    INDEX
    Explanations

    Nootropics

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the Italian term “nootropici” (or its sub‐token fragments “ot rop ici”), i.e. mentions of nootropic compounds in Italian.

    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
     вспом
    -0.07
    749
    -0.07
     Vocabulary
    -0.06
    .MM
    -0.06
     περιοχή
    -0.06
     řid
    -0.06
    зь
    -0.06
     Esk
    -0.06
     ноября
    -0.06
    RSS
    -0.06
    POSITIVE LOGITS
     draft
    0.07
    총
    0.06
    -cn
    0.06
    κό
    0.06
    Marvel
    0.06
     accredited
    0.06
     astonished
    0.06
     beats
    0.06
     WebDriver
    0.06
    pheric
    0.06
    Activations Density 0.004%

    No Known Activations