© 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. 90605
    Prev
    Next
    INDEX
    Explanations

    enough

    np_max-act · gemini-2.0-flash

    issues related to customer service and support dialogues.

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

    The neuron selectively responds to the word “enough.”

    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
    stit
    -0.08
    zel
    -0.07
    yt
    -0.07
    yl
    -0.07
     Toni
    -0.07
    zon
    -0.07
     Glory
    -0.07
     racer
    -0.07
    y
    -0.07
    zial
    -0.07
    POSITIVE LOGITS
     enough
    0.13
     Enough
    0.13
    Enough
    0.12
    ough
    0.07
    _gshared
    0.07
     Farage
    0.07
    EQ
    0.07
    フト
    0.07
    UGH
    0.07
    ().'
    0.07
    Activations Density 0.011%

    No Known Activations