© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92176
    Prev
    Next
    INDEX
    Explanations

    math equations with variables

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of a multiplication operator directly followed by a single-letter variable (e.g. “* b,” “* z,” “* k”).

    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
     bại
    -0.07
    ednou
    -0.07
    Insensitive
    -0.07
    .TH
    -0.06
    เส
    -0.06
     Vid
    -0.06
    _trees
    -0.06
     Howe
    -0.06
    .EventSystems
    -0.06
    Approved
    -0.06
    POSITIVE LOGITS
    (resultSet
    0.06
    potential
    0.06
    (sa
    0.06
     overlooked
    0.06
    '>
    0.06
    102
    0.06
     증
    0.06
    ">↵↵
    0.06
    	       
    0.06
     militant
    0.06
    Activations Density 0.005%

    No Known Activations