Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 91118
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric expressions that specify word or item counts (e.g. “three words,” “two words,” “one word”).

    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
    .barDockControl
    -0.07
    ContentLoaded
    -0.07
     QList
    -0.07
     득
    -0.07
    自由
    -0.07
    $LANG
    -0.06
    $ar
    -0.06
    监听页面
    -0.06
    DataRow
    -0.06
     základ
    -0.06
    POSITIVE LOGITS
    园
    0.06
    icture
    0.06
    流量
    0.06
     LT
    0.06
    _countries
    0.06
     RG
    0.06
    στο
    0.06
    ???
    0.06
    _vs
    0.06
    ////////
    0.06
    Activations Density 0.011%

    No Known Activations