© 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. 126411
    Prev
    Next
    INDEX
    Explanations

    technical/scientific fragments

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing decimal (floating-point) values.

    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
     detained
    -0.08
     FIXED
    -0.06
     Rather
    -0.06
     passengers
    -0.06
     documenting
    -0.06
    /tasks
    -0.06
     recalling
    -0.06
    ungkin
    -0.06
    Invocation
    -0.06
     recommends
    -0.06
    POSITIVE LOGITS
     tossing
    0.07
    =res
    0.07
    ажд
    0.07
     seper
    0.07
     склад
    0.06
    .getStatus
    0.06
     rtc
    0.06
     Comes
    0.06
    forgot
    0.06
    ]):
↵
    0.06
    Activations Density 2.145%

    No Known Activations