© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 88987
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    mathematical concepts or operations described in a mathematical context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on occurrences of the “+” sign in arithmetic expressions, i.e. addition operators.

    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
     Scriptures
    -0.06
    Management
    -0.06
     Mec
    -0.06
    ()=="
    -0.06
     bushes
    -0.06
     дополнитель
    -0.06
     burst
    -0.06
    Creat
    -0.06
     numar
    -0.06
    beros
    -0.06
    POSITIVE LOGITS
    (defun
    0.07
    "),
↵
    0.07
    剣
    0.06
    ?id
    0.06
    setItem
    0.06
    JsonValue
    0.06
    Responder
    0.06
     verse
    0.06
    ,obj
    0.06
     mined
    0.06
    Activations Density 0.024%

    No Known Activations