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. 40395
    Prev
    Next
    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash

    The neuron reliably activates on occurrences of the word “support” (and its inflected forms).

    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
     calibrated
    -0.08
    -->↵↵
    -0.07
     hsv
    -0.07
     until
    -0.07
     Synthetic
    -0.07
    31
    -0.06
     Travel
    -0.06
     Will
    -0.06
    =True
    -0.06
     encountered
    -0.06
    POSITIVE LOGITS
     support
    0.11
     supports
    0.10
     supporting
    0.10
     supported
    0.09
     Support
    0.08
    -supported
    0.08
    Swagger
    0.07
     Supporters
    0.07
     buoy
    0.07
     podporu
    0.07
    Activations Density 0.036%

    No Known Activations