© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    phrases related to coffee brewing techniques and their effects on flavor quality

    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
    usercontent
    -0.08
    erif
    -0.08
    uvo
    -0.07
    tae
    -0.07
    ienda
    -0.07
    azo
    -0.07
    Ñİн
    -0.07
    orrh
    -0.07
     entityId
    -0.07
    ocha
    -0.07
    POSITIVE LOGITS
    arget
    0.06
    arel
    0.06
    ullet
    0.06
    coe
    0.06
    ig
    0.06
     und
    0.06
    rac
    0.05
     disc
    0.05
    gard
    0.05
     cl
    0.05
    Activations Density 0.007%

    No Known Activations