© 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. 125959
    Prev
    Next
    INDEX
    Explanations

    CSS length units

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric measurement tokens—especially CSS length or dimension values (numbers, decimals, and units).

    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
    ився
    -0.07
     getStatus
    -0.07
     cultures
    -0.07
     layered
    -0.07
    _datas
    -0.07
    (wp
    -0.07
     Aless
    -0.06
    clusters
    -0.06
     tangent
    -0.06
     Рос
    -0.06
    POSITIVE LOGITS
    ?>'
    0.06
    ้องก
    0.06
    .Std
    0.06
    zend
    0.06
    ันธ
    0.06
    .Top
    0.05
     prominent
    0.05
     perish
    0.05
    _Clear
    0.05
    .";
↵
    0.05
    Activations Density 0.007%

    No Known Activations