© 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. 19-RESID-POST-AA
    6. 87805
    Prev
    Next
    INDEX
    Explanations

    limits

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     다음과
    -0.07
    aph
    -0.06
    equals
    -0.06
    ід
    -0.06
    еви
    -0.06
     الذهاب
    -0.06
     kor
    -0.06
    Eye
    -0.06
     υπό
    -0.06
     accumulating
    -0.06
    POSITIVE LOGITS
    conom
    0.07
    .html
    0.07
    /validation
    0.06
     MQTT
    0.06
    _REF
    0.06
    aji
    0.06
    -touch
    0.06
    riott
    0.06
    Muon
    0.06
    >".$
    0.06
    Activations Density 0.101%

    No Known Activations