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

    Neuronpedia

    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. 82290
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals and their achievements

    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
    qua
    -0.07
    lek
    -0.07
    olet
    -0.07
    Rendering
    -0.07
    cop
    -0.07
    ozor
    -0.07
     '<%=
    -0.07
    ocop
    -0.07
    phia
    -0.07
    cak
    -0.07
    POSITIVE LOGITS
     Episode
    0.07
     episode
    0.07
     host
    0.07
    пÑĢиклад
    0.06
     podcast
    0.06
    _ld
    0.06
     (@
    0.06
     discussing
    0.06
     discuss
    0.06
     talk
    0.06
    Activations Density 0.014%

    No Known Activations