© 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. 73262
    Prev
    Next
    INDEX
    Explanations

    references to cocktails 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
    Ùĩ
    -0.08
    à¹Ĩ
    -0.07
    HomeAsUp
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    ccount
    -0.07
    eed
    -0.07
    eload
    -0.06
    /control
    -0.06
    gorm
    -0.06
    lessly
    -0.06
    POSITIVE LOGITS
    swith
    0.09
    /mock
    0.07
    tails
    0.07
    zsche
    0.07
    rete
    0.07
    ery
    0.07
    swana
    0.07
    ry
    0.06
    ivities
    0.06
    to
    0.06
    Activations Density 0.004%

    No Known Activations