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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123052
    Prev
    Next
    INDEX
    Explanations

    Technical specifications / emails

    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
     ถ
    -0.07
     comprising
    -0.07
    -chan
    -0.07
     aest
    -0.06
    YOU
    -0.06
     INC
    -0.06
    -so
    -0.06
     Cout
    -0.06
    entin
    -0.06
    ẳn
    -0.06
    POSITIVE LOGITS
    Lng
    0.06
    Grad
    0.06
    agnetic
    0.06
    adder
    0.06
     Lens
    0.06
    存档备份
    0.06
    =explode
    0.05
    _TX
    0.05
    np
    0.05
    plet
    0.05
    Activations Density 0.000%

    No Known Activations