© 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. 88950
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    semantic matches between sentences expressing similar opinions on a topic.

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

    This neuron activates on numeric markers and labels that enumerate or index sentences (e.g. “2,” “sentence 1,” “sentence 2”), effectively detecting the numbered-sentence references in the text.

    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
    Obsolete
    -0.06
    ひと
    -0.06
    .Embed
    -0.06
    205
    -0.06
    _PLL
    -0.06
     入
    -0.06
    current
    -0.06
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.06
    ControlEvents
    -0.06
    PLUGIN
    -0.06
    POSITIVE LOGITS
     flor
    0.07
     Filipino
    0.07
    )$
    0.07
                 ↵
    0.06
     mí
    0.06
    */,
    0.06
     pals
    0.06
     Sabha
    0.06
    　ﾊ
    0.06
    (pid
    0.06
    Activations Density 0.009%

    No Known Activations