© 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. 12685
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on CSS/jQuery animation and transform keywords (e.g. translate, slide, top) indicating it’s looking for animation‐related property names and values.

    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
     dí
    -0.07
     Fay
    -0.07
    $log
    -0.07
    "]);↵↵
    -0.06
     над
    -0.06
     referencedColumnName
    -0.06
    428
    -0.06
     findAll
    -0.06
    -at
    -0.06
     '');↵
    -0.06
    POSITIVE LOGITS
    ยาว
    0.07
    ем
    0.07
     Compatibility
    0.07
    ,c
    0.06
    크
    0.06
     configurations
    0.06
     Ordering
    0.06
    ubber
    0.06
     Athletics
    0.06
    =findViewById
    0.06
    Activations Density 0.020%

    No Known Activations