© 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. 125270
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Thousands
    -0.08
    stras
    -0.06
     accesses
    -0.06
    尖
    -0.06
    anes
    -0.06
    _passed
    -0.06
    ieces
    -0.06
    inas
    -0.06
    NONE
    -0.06
    (Schedulers
    -0.06
    POSITIVE LOGITS
    .Volume
    0.06
    ブリ
    0.06
    роб
    0.06
     환경
    0.06
    Compatibility
    0.06
     個
    0.06
     SST
    0.06
     Dash
    0.06
     fl
    0.06
    	events
    0.06
    Activations Density 0.144%

    No Known Activations