© 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. 127281
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific research and publications in genetics

    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
    riel
    -0.08
    lichen
    -0.07
    گز
    -0.07
     доÑĢож
    -0.07
    lich
    -0.07
    ADATA
    -0.07
    /devices
    -0.07
    developers
    -0.07
    ducted
    -0.07
    ALSE
    -0.07
    POSITIVE LOGITS
    (D
    0.07
    @d
    0.07
    (DE
    0.07
    =D
    0.07
    (DB
    0.06
     Don
    0.06
    Do
    0.06
     Do
    0.06
    (Dialog
    0.06
    .promise
    0.06
    Activations Density 1.408%

    No Known Activations