© 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 EvalsExportsAPI 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. 59203
    Prev
    Next
    INDEX
    Explanations

    references to coffee and its consumption effects

    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
     favourite
    -0.07
    dek
    -0.07
    &E
    -0.06
    è¾ij
    -0.06
    -www
    -0.06
    ìī¬
    -0.06
     Predator
    -0.06
     hoá
    -0.06
     Frequently
    -0.06
     Zub
    -0.06
    POSITIVE LOGITS
    ftype
    0.07
    cano
    0.07
    ../../../../
    0.07
     Burgess
    0.07
    adil
    0.06
    adel
    0.06
    ramid
    0.06
    ,
    0.06
    _COND
    0.06
    ffen
    0.06
    Activations Density 0.000%

    No Known Activations