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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16408
    Prev
    Next
    INDEX
    Explanations

    references to specific authors and characters in literary contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :UIAlert
    -0.07
    _HERSHEY
    -0.07
    _exempt
    -0.07
    )((((
    -0.07
    _Tis
    -0.07
    -fontawesome
    -0.07
    fragistics
    -0.06
    :UITableView
    -0.06
    TriState
    -0.06
    istrovstvÃŃ
    -0.06
    POSITIVE LOGITS
    #ac
    0.09
    .Reporting
    0.08
    âĢ¦"↵↵
    0.08
     recep
    0.08
    اÙĨÙĩ
    0.07
     proje
    0.07
     âĶĢ
    0.07
    (PC
    0.07
     ↵↵
    0.07
     zbo
    0.07
    Activations Density 0.408%

    No Known Activations