© 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. 68855
    Prev
    Next
    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens with decimal points.

    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
     Klan
    -0.06
    utton
    -0.06
     Pipes
    -0.06
    .partner
    -0.06
     Replica
    -0.06
    orang
    -0.06
     melt
    -0.06
    ६
    -0.05
    .rotate
    -0.05
     destruction
    -0.05
    POSITIVE LOGITS
     cenu
    0.07
     Local
    0.07
     Als
    0.07
     Verify
    0.07
     srov
    0.06
    вердж
    0.06
     میل
    0.06
     나오
    0.06
     něj
    0.06
    going
    0.06
    Activations Density 0.008%

    No Known Activations