© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 126087
    Prev
    Next
    INDEX
    Explanations

    dates and temporal references

    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
     meme
    -0.06
     mgr
    -0.05
    avar
    -0.05
     mmc
    -0.05
     EMC
    -0.05
    .getRandom
    -0.05
    vos
    -0.05
    оÑĢм
    -0.05
     Pet
    -0.05
     Zuk
    -0.05
    POSITIVE LOGITS
     Laden
    0.07
    ohen
    0.07
    beros
    0.07
    haled
    0.07
    bens
    0.07
    onth
    0.07
    .feed
    0.06
    dux
    0.06
    identifier
    0.06
    foy
    0.06
    Activations Density 0.001%

    No Known Activations