© 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
    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. 68997
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    legal terms and references related to court cases and filings.

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

    The neuron responds to sentence‐ending punctuation—especially the period token that marks the end of a sentence.

    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
     officers
    -0.06
     prolet
    -0.06
    Officers
    -0.06
     tapping
    -0.06
     epoch
    -0.06
    Plugin
    -0.06
     meetings
    -0.06
    nist
    -0.06
     publish
    -0.06
     officer
    -0.06
    POSITIVE LOGITS
     uvědom
    0.07
    곡
    0.06
    ��
    0.06
     wealthy
    0.06
    __);↵↵
    0.06
    dbContext
    0.06
    idences
    0.06
     سبب
    0.06
    enido
    0.06
    -utils
    0.06
    Activations Density 0.005%

    No Known Activations