© 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. 59118
    Prev
    Next
    INDEX
    Explanations

    references to policies, laws, and historical government actions

    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
    िषय
    -0.07
    ãģĦãĤĭ
    -0.06
    edom
    -0.06
    acerb
    -0.06
    elay
    -0.06
    ?f
    -0.06
    baugh
    -0.06
     moist
    -0.06
     Fired
    -0.06
     hopefully
    -0.06
    POSITIVE LOGITS
     decades
    0.08
     originally
    0.07
     ëĭ¹ìĭľ
    0.07
    -cols
    0.07
     original
    0.07
    以æĿ¥
    0.07
     prom
    0.07
    197
    0.06
    ajo
    0.06
    entifier
    0.06
    Activations Density 0.029%

    No Known Activations