© 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. 123713
    Prev
    Next
    INDEX
    Explanations

    references to configuration settings and related terms

    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
    dür
    -0.07
    ร
    -0.07
    lest
    -0.07
    kin
    -0.06
    ikes
    -0.06
    Ø©
    -0.06
    ··
    -0.06
    _TIM
    -0.06
    LY
    -0.06
    hood
    -0.06
    POSITIVE LOGITS
    ra
    0.09
    inct
    0.09
    urator
    0.08
    na
    0.08
    urations
    0.08
    elli
    0.08
    nas
    0.08
    uart
    0.08
    opher
    0.08
    ASSERT
    0.08
    Activations Density 0.017%

    No Known Activations