© 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 EvalsExportsinterp-engineNEWAPI 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. 18022
    Prev
    Next
    INDEX
    Explanations

    references to specific items or subjects being discussed

    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
    erus
    -0.07
    082
    -0.06
    .Unicode
    -0.06
     tane
    -0.06
    isté
    -0.06
    processable
    -0.06
    luet
    -0.06
    ÑĨи
    -0.06
    ens
    -0.06
    086
    -0.05
    POSITIVE LOGITS
     kind
    0.13
     type
    0.11
     kinds
    0.11
     genre
    0.10
     sort
    0.10
     ilk
    0.10
    .kind
    0.09
    kind
    0.09
     jinak
    0.09
     format
    0.09
    Activations Density 0.032%

    No Known Activations