© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9010
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash

    This neuron detects phrases expressing a numeric threshold comparison (e.g. “Less than X …”).

    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
    70
    -0.07
    372
    -0.07
    269
    -0.07
     nø
    -0.07
    Moreover
    -0.06
     Hol
    -0.06
    avigation
    -0.06
     gums
    -0.06
     Gy
    -0.06
     discretion
    -0.06
    POSITIVE LOGITS
    UNCT
    0.08
    unta
    0.08
    анта
    0.07
    atoes
    0.07
    ACHI
    0.07
     than
    0.07
     Than
    0.07
    0.07
    čka
    0.07
     <
    0.06
    Activations Density 0.008%

    No Known Activations