© 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. 29073
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases within legal or formal 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
    ì§Ģëħ¸
    -0.09
     ############################################################################
    -0.08
    alama
    -0.08
    erus
    -0.07
    richt
    -0.07
    EDIA
    -0.07
    ãĥĩãĤ£ãĤ¢
    -0.07
    à¹Ĥล
    -0.07
    ëĶĶìĭľ
    -0.07
    coe
    -0.07
    POSITIVE LOGITS
     handjob
    0.07
    @testable
    0.06
    irt
    0.05
     mushroom
    0.05
    lick
    0.05
     Vine
    0.05
     proofs
    0.05
    缣
    0.05
    .printStackTrace
    0.05
    vid
    0.05
    Activations Density 0.013%

    No Known Activations