© 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. 88945
    Prev
    Next
    INDEX
    Explanations

    agreements or conditions

    np_max-act · gemini-2.0-flash

    This neuron detects words that express amount or degree—intensifiers and quantifiers such as bit, deal, terms, too, and great.

    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
    .D
    -0.07
     Frequency
    -0.06
    .Link
    -0.06
    criptions
    -0.06
    INCREMENT
    -0.06
    ensely
    -0.06
     ultimately
    -0.06
    older
    -0.06
    unding
    -0.06
     preschool
    -0.06
    POSITIVE LOGITS
     запит
    0.06
     حر
    0.06
     Định
    0.06
     виды
    0.06
    launch
    0.06
    ='_
    0.06
     nabíd
    0.06
    )test
    0.06
    ::$_
    0.06
     механіз
    0.06
    Activations Density 0.369%

    No Known Activations