© 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. 91990
    Prev
    Next
    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    file paths and commands related to programming or software development.

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

    The neuron primarily fires on floating-point numeric literals (i.e. numbers containing a decimal point).

    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
     Gareth
    -0.07
    _TRANSFER
    -0.06
     predators
    -0.06
     svůj
    -0.06
    牧
    -0.06
    σή
    -0.06
    tolower
    -0.06
     جديد
    -0.06
     cascade
    -0.06
     πλη
    -0.06
    POSITIVE LOGITS
     specializes
    0.06
     tên
    0.06
    _NULL
    0.06
     never
    0.06
     rented
    0.06
     Jean
    0.06
     olmaz
    0.06
    ählen
    0.06
    ัตน
    0.06
     село
    0.06
    Activations Density 0.006%

    No Known Activations