© 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. 30442
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron fires on the prepositions “in” and “by” when they head locative or agent phrases—especially in passive‐voice contexts.

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

    terms related to medical devices and their classifications.

    oai_token-act-pair · gpt-4o-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
    »:
    -0.07
    ITT
    -0.06
    紹介
    -0.06
     바랍니다
    -0.06
    WARNING
    -0.06
     invalid
    -0.06
     windows
    -0.06
     única
    -0.06
     इस
    -0.06
     Unsupported
    -0.06
    POSITIVE LOGITS
    seg
    0.06
     rhyth
    0.06
    thro
    0.06
    guna
    0.06
    (pos
    0.06
    ยา
    0.06
     Buckley
    0.06
    _vocab
    0.06
     соверш
    0.06
     escapes
    0.06
    Activations Density 0.141%

    No Known Activations