© 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. 56621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating combinations or pairings of elements

    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
    bose
    -0.08
    .camel
    -0.08
    esy
    -0.08
    ÑĩаÑĤ
    -0.07
    edata
    -0.07
    zell
    -0.07
    usto
    -0.07
    gens
    -0.07
    FileVersion
    -0.07
    ["$
    -0.07
    POSITIVE LOGITS
     other
    0.18
    other
    0.16
     others
    0.12
    åħ¶ä»ĸ
    0.12
     otras
    0.11
    Other
    0.11
     altri
    0.11
     Other
    0.10
     altre
    0.10
     otros
    0.10
    Activations Density 0.038%

    No Known Activations