© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash

    The neuron fires on medical adjectives denoting pathological conditions or tissue/disease states (e.g. hemorrhagic, cystic, purulent, stenosing).

    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
    (te
    -0.07
     groom
    -0.06
    	Vk
    -0.06
    ////////////////////////////////////////////////////////////
    -0.06
    这些
    -0.06
     insult
    -0.06
    (re
    -0.06
    .BackgroundImageLayout
    -0.06
    (ch
    -0.06
     Vz
    -0.06
    POSITIVE LOGITS
     oben
    0.07
    plet
    0.07
     loi
    0.06
    Undo
    0.06
    .rename
    0.06
    irt
    0.06
     firefight
    0.06
    ясь
    0.06
     Bilder
    0.06
     bàn
    0.06
    Activations Density 0.053%

    No Known Activations