© 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
    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. 113890
    Prev
    Next
    INDEX
    Explanations

    example

    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
    osals
    -0.07
     Trick
    -0.06
     took
    -0.06
     Werk
    -0.06
     proposal
    -0.06
     CMD
    -0.06
     autour
    -0.06
     fora
    -0.06
    消
    -0.06
    iant
    -0.06
    POSITIVE LOGITS
     mé
    0.07
    題
    0.06
    김
    0.06
    _]
    0.06
    ray
    0.06
     boh
    0.06
    _NS
    0.06
    ΟΛΟΓ
    0.06
     okhttp
    0.06
    .assertIsInstance
    0.06
    Activations Density 0.062%

    No Known Activations