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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78654
    Prev
    Next
    INDEX
    Explanations

    references to movement or exchange in various contexts

    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
    uhan
    -0.06
    chaft
    -0.06
    rana
    -0.06
    .dr
    -0.06
     straight
    -0.06
     bund
    -0.06
    ÏĦÏģα
    -0.06
     sẵn
    -0.06
     initialValues
    -0.06
    die
    -0.06
    POSITIVE LOGITS
     between
    0.13
    between
    0.13
     междÑĥ
    0.12
    -between
    0.11
    ä¹ĭéĹ´
    0.11
     interchange
    0.11
    etween
    0.10
     Between
    0.10
    Between
    0.10
     zwischen
    0.10
    Activations Density 0.125%

    No Known Activations