Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40641
    Prev
    Next
    INDEX
    Explanations

    punctuation, separators

    np_max-act · gemini-2.0-flash

    information related to surgical treatments and rehabilitation for thyroid eye disease (TED).

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

    The neuron detects common connective and summary terms that introduce or link list items or key points (e.g. “including,” “and,” “goals,” “components,” “also,” “potential”).

    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
    えば
    -0.06
     costo
    -0.06
    Input
    -0.06
     forb
    -0.06
    lambda
    -0.05
     "{{
    -0.05
     spawn
    -0.05
    _hit
    -0.05
     res
    -0.05
     законодав
    -0.05
    POSITIVE LOGITS
     운영자
    0.07
     Blend
    0.07
     vara
    0.07
    qa
    0.06
     Personen
    0.06
     fontWithName
    0.06
     العمل
    0.06
     peníze
    0.06
     �
    0.06
     Berk
    0.06
    Activations Density 0.091%

    No Known Activations