© 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. 6444
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    The neuron detects comparative intensifier adverbs—words like “more” and “further” that amplify or extend an action.

    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
    Yaw
    -0.06
    insula
    -0.06
     Brewery
    -0.06
    によ
    -0.06
    電視
    -0.06
     몇
    -0.06
     bitch
    -0.06
    aeda
    -0.06
     Gaga
    -0.06
     Erdoğan
    -0.06
    POSITIVE LOGITS
    _initialize
    0.07
    onChange
    0.07
    usable
    0.07
     Pharmac
    0.07
     optionally
    0.07
     центра
    0.07
    hang
    0.07
    **)
    0.06
     onclick
    0.06
     mothers
    0.06
    Activations Density 0.014%

    No Known Activations