© 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. 89869
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on the markup delimiters (“<” and related tokens) used to open or close HTML/JSX tags.

    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
    \Log
    -0.07
     shoulder
    -0.07
    al
    -0.07
    _dict
    -0.06
     photons
    -0.06
    locales
    -0.06
    ,event
    -0.06
     hire
    -0.06
    _pdf
    -0.06
    Reducers
    -0.06
    POSITIVE LOGITS
     Fog
    0.07
    vez
    0.06
    ！↵↵↵↵
    0.06
     VX
    0.06
    طي
    0.06
     UIPickerView
    0.06
     Ç
    0.06
    지가
    0.06
     Traverse
    0.06
    _visited
    0.06
    Activations Density 0.002%

    No Known Activations