© 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. 9-LLAMASCOPE-RES-131K
    11. 98726
    Prev
    Next
    INDEX
    Explanations

    information related to preparing and brewing coffee, specifically espresso

    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
    коÑĤ
    -0.07
    úa
    -0.06
    ubit
    -0.06
     дод
    -0.06
     shrink
    -0.06
    licken
    -0.06
    ÏĦÏĮ
    -0.06
     ThemeData
    -0.06
     Industry
    -0.06
    portun
    -0.06
    POSITIVE LOGITS
    _fwd
    0.07
    lerce
    0.07
    urb
    0.07
     Preston
    0.06
    uzz
    0.06
    .bpm
    0.06
    ellas
    0.06
    morph
    0.06
    lep
    0.06
    reten
    0.06
    Activations Density 0.051%

    No Known Activations