© 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. 121156
    Prev
    Next
    INDEX
    Explanations

    time-related references, specifically indicating timestamps

    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
    elsen
    -0.06
     flank
    -0.06
    =__
    -0.06
    rint
    -0.06
    .weixin
    -0.05
    renom
    -0.05
    zim
    -0.05
     ag
    -0.05
    .ejb
    -0.05
    acz
    -0.05
    POSITIVE LOGITS
    殿
    0.07
    áš
    0.07
    ioni
    0.07
     nackte
    0.07
     пÑĥÑĤ
    0.07
    ç²Ĵ
    0.07
     incarcer
    0.06
    FER
    0.06
    ungeon
    0.06
    sez
    0.06
    Activations Density 0.002%

    No Known Activations