© 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. 125127
    Prev
    Next
    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash

    The neuron is looking for the degree-modifier “too” when it’s used to intensify an adjective or adverb.

    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
     '&
    -0.07
    .clipsToBounds
    -0.07
    .mkdirs
    -0.07
    (user
    -0.07
    leniyor
    -0.07
     उपलब
    -0.06
    _percent
    -0.06
    divid
    -0.06
     داشت
    -0.06
     cubic
    -0.06
    POSITIVE LOGITS
    TT
    0.07
    CAA
    0.07
     tm
    0.07
    čním
    0.07
     curry
    0.07
    tpl
    0.06
    RK
    0.06
     unb
    0.06
    lim
    0.06
     lime
    0.06
    Activations Density 0.005%

    No Known Activations