© 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. 68758
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the phrase “it means,” flagging instances where the text is defining or explaining meaning.

    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
    $log
    -0.07
    (ad
    -0.07
    (fin
    -0.06
    |h
    -0.06
     deepcopy
    -0.06
    �
    -0.06
    되었
    -0.06
    Hat
    -0.06
    g
    -0.06
    0
    -0.06
    POSITIVE LOGITS
     znamená
    0.07
     it
    0.07
     It
    0.07
    America
    0.07
    ennial
    0.06
    柱
    0.06
     gl
    0.06
    ením
    0.06
     qemu
    0.06
    ്�
    0.06
    Activations Density 0.015%

    No Known Activations