© 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. 15-LLAMASCOPE-RES-131K
    11. 87703
    Prev
    Next
    INDEX
    Explanations

    specific time intervals related to events or activities

    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
    çĬ¶
    -0.08
    quist
    -0.08
    inho
    -0.07
    agi
    -0.07
    Ïĥη
    -0.07
    urus
    -0.07
    ض
    -0.07
    ayd
    -0.07
    /of
    -0.07
    ál
    -0.07
    POSITIVE LOGITS
     rowspan
    0.07
     dia
    0.06
    ged
    0.06
     factor
    0.06
    gba
    0.06
    -archive
    0.05
    ãĥ¡ãĥ³ãĥĪ
    0.05
     factorial
    0.05
    antry
    0.05
    leanup
    0.05
    Activations Density 0.003%

    No Known Activations