© 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. 30432
    Prev
    Next
    INDEX
    Explanations

    Off

    np_max-act · gemini-2.0-flash

    The neuron detects the blog‐style “Comments Off” (and related comment-section labels) UI element.

    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
     red
    -0.07
    dül
    -0.07
    産
    -0.07
    coholic
    -0.07
    .tintColor
    -0.07
     đỏ
    -0.07
     Irma
    -0.06
    Crit
    -0.06
     zak
    -0.06
     ppm
    -0.06
    POSITIVE LOGITS
     Words
    0.06
     перевір
    0.06
     Twins
    0.06
     thì
    0.06
    BF
    0.06
    	echo
    0.06
    αλύτε
    0.06
     Без
    0.06
     expres
    0.06
    .createElement
    0.06
    Activations Density 0.002%

    No Known Activations