© 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. 15-RESID-POST-AA
    11. 20073
    Prev
    Next
    INDEX
    Explanations

    ionic liquids and chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owe
    -0.07
    906
    -0.06
    -selection
    -0.06
     всі
    -0.06
    hů
    -0.06
     First
    -0.06
    First
    -0.06
     Hulu
    -0.06
    rin
    -0.06
    tea
    -0.06
    POSITIVE LOGITS
    UPPORT
    0.07
     achieving
    0.07
    _unset
    0.07
    _FL
    0.06
    Features
    0.06
     RootState
    0.06
     populace
    0.06
    navigate
    0.06
     Compatible
    0.06
     ery
    0.06
    Activations Density 0.051%

    No Known Activations