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. 15412
    Prev
    Next
    INDEX
    Explanations

    technical or code snippets

    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
     orient
    -0.07
     близ
    -0.07
     domácí
    -0.07
    visible
    -0.07
    	TR
    -0.06
    ecký
    -0.06
    encode
    -0.06
    .createObject
    -0.06
     calmly
    -0.06
     никто
    -0.06
    POSITIVE LOGITS
    113
    0.07
    <nav
    0.06
    AF
    0.06
    lesai
    0.06
    114
    0.06
    iction
    0.06
     Lug
    0.06
     workplaces
    0.06
    _CONSOLE
    0.05
    93
    0.05
    Activations Density 0.000%

    No Known Activations