© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 107626
    Prev
    Next
    INDEX
    Explanations

    the

    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
     flips
    -0.06
    -tip
    -0.06
    chedulers
    -0.06
    _hard
    -0.06
    _restrict
    -0.06
     headlights
    -0.06
    ارک
    -0.06
    \Factory
    -0.06
    AJOR
    -0.06
    isd
    -0.05
    POSITIVE LOGITS
     民
    0.08
     Lok
    0.07
     Comfort
    0.07
    comfort
    0.07
     Comments
    0.07
     focusing
    0.07
     remembered
    0.07
     велик
    0.07
    ापक
    0.07
    健康
    0.07
    Activations Density 0.000%

    No Known Activations