© 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. 26037
    Prev
    Next
    INDEX
    Explanations

    Science articles

    np_max-act · gemini-2.0-flash

    discussions about cellular signaling and regulation related to growth and disease.

    oai_token-act-pair · gpt-4o-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
     化
    -0.08
    OT
    -0.07
    Proxy
    -0.07
    rain
    -0.07
     PCB
    -0.07
    _grid
    -0.06
    ain
    -0.06
     transmission
    -0.06
    ek
    -0.06
    icao
    -0.06
    POSITIVE LOGITS
     Borg
    0.07
    して
    0.06
    ={}↵
    0.06
    _producto
    0.06
     Duy
    0.06
     kommun
    0.06
    ǎ
    0.06
     nedir
    0.06
    isce
    0.06
    /test
    0.06
    Activations Density 0.046%

    No Known Activations