© 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. 106386
    Prev
    Next
    INDEX
    Explanations

    references to significant disruptions or changes in situations

    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
    pty
    -0.07
    .scalablytyped
    -0.07
    rg
    -0.07
     ince
    -0.07
    HORT
    -0.06
    xml
    -0.06
    _Impl
    -0.06
    SetTitle
    -0.06
    iam
    -0.06
    anova
    -0.06
    POSITIVE LOGITS
     our
    0.08
    [s
    0.08
     [
    0.07
    [e
    0.07
    [to
    0.07
     [$
    0.07
    æĪij们çļĦ
    0.07
     ourselves
    0.07
     [_
    0.07
     vår
    0.07
    Activations Density 0.034%

    No Known Activations