Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 30273
    Prev
    Next
    INDEX
    Explanations

    listening/watching later offline

    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
     sens
    -0.07
    いい
    -0.06
    UG
    -0.06
     passes
    -0.06
     Starting
    -0.06
     vais
    -0.06
     Garmin
    -0.06
    Na
    -0.06
     fan
    -0.06
     Damian
    -0.06
    POSITIVE LOGITS
    pee
    0.07
    집
    0.06
     баг
    0.06
    芯
    0.06
    ampled
    0.06
     Maced
    0.06
     sturdy
    0.06
     concentrated
    0.06
    概
    0.06
    elic
    0.06
    Activations Density 0.073%

    No Known Activations