© 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. 5-LLAMASCOPE-RES-131K
    11. 126978
    Prev
    Next
    INDEX
    Explanations

    references to citations or footnotes in a document

    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
    atism
    -0.07
    ien
    -0.07
     addCriterion
    -0.07
     paddingHorizontal
    -0.07
    ander
    -0.07
    ims
    -0.06
    amar
    -0.06
    ean
    -0.06
    chn
    -0.06
    imal
    -0.06
    POSITIVE LOGITS
    ListNode
    0.07
    kla
    0.07
    mnop
    0.07
    ÑĩÑĥ
    0.07
    STALL
    0.07
     ráp
    0.07
    Äįen
    0.07
    162
    0.07
    evin
    0.06
     LRV
    0.06
    Activations Density 0.012%

    No Known Activations