© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92142
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially on decimal numbers and other numeric 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
     appointments
    -0.07
    Clear
    -0.07
    .csv
    -0.07
     Monitoring
    -0.06
     Café
    -0.06
     habits
    -0.06
    appointment
    -0.06
     formulation
    -0.06
    Partial
    -0.06
    Segue
    -0.06
    POSITIVE LOGITS
    ustry
    0.07
     Yol
    0.06
    (elm
    0.06
    _CR
    0.06
    /upload
    0.06
     �
    0.06
     �
    0.06
     Télé
    0.06
     multit
    0.06
    .frequency
    0.06
    Activations Density 0.773%

    No Known Activations