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. 40492
    Prev
    Next
    INDEX
    Explanations

    hydration

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the word “hydration” (and its variants) in the text.

    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
    141
    -0.08
     uncont
    -0.07
     coup
    -0.07
    /false
    -0.06
     مسئله
    -0.06
    292
    -0.06
     skepticism
    -0.06
     професій
    -0.06
     lee
    -0.06
     celle
    -0.06
    POSITIVE LOGITS
     hydration
    0.12
    dration
    0.11
     dehydration
    0.10
    hydrate
    0.10
     hydrated
    0.10
    hydration
    0.09
    hydr
    0.09
     hydr
    0.08
    ER
    0.08
    ات
    0.07
    Activations Density 0.004%

    No Known Activations