© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30666
    Prev
    Next
    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash

    academic language related to theoretical physics and mathematical concepts.

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

    The neuron activates on numeric tokens (e.g. affiliation/address numbers and decimal 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
     kon
    -0.06
    ump
    -0.06
    avigator
    -0.06
     tiles
    -0.06
     failure
    -0.06
    id
    -0.06
     mates
    -0.06
    661
    -0.06
     drowning
    -0.06
    442
    -0.06
    POSITIVE LOGITS
     Newtonsoft
    0.07
     FRE
    0.07
    @register
    0.07
     accessor
    0.06
    tplib
    0.06
    ΟΚ
    0.06
    eax
    0.06
    σσότε
    0.06
    구글상위
    0.06
    [action
    0.06
    Activations Density 0.009%

    No Known Activations