© 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. 128875
    Prev
    Next
    INDEX
    Explanations

    contractions

    np_max-act · gemini-2.0-flash

    This neuron activates on common English contractions (tokens containing apostrophes such as "I'm," "he's," "don't," "I'll," etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    English contracted forms (words with apostrophes like I'm, he's, we're, there's, n't).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    !!!!!!!!
    -0.07
    เสน
    -0.07
    仅
    -0.06
    Дж
    -0.06
     ($)
    -0.06
    �乐
    -0.06
    ५
    -0.06
    .Must
    -0.06
     ulus
    -0.06
    permission
    -0.06
    POSITIVE LOGITS
    ’re
    0.07
     ngược
    0.07
    Go
    0.07
    apore
    0.07
    ’ve
    0.07
    're
    0.07
     impoverished
    0.07
    tolower
    0.06
    ISCO
    0.06
    ısına
    0.06
    Activations Density 0.215%

    No Known Activations