© 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. 71257
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or deadlines, particularly related to 24 and 48 hours

    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
    $MESS
    -0.07
     fitte
    -0.07
     MetroFramework
    -0.07
    agens
    -0.06
    олева
    -0.06
    shi
    -0.06
    logue
    -0.06
    oshi
    -0.06
    urgent
    -0.06
    ãĥ³ãĤº
    -0.06
    POSITIVE LOGITS
    roud
    0.06
    avel
    0.06
    abbo
    0.06
    çī
    0.06
    UTC
    0.06
    andbox
    0.06
     treatment
    0.06
    ombat
    0.06
     forgot
    0.06
    romo
    0.06
    Activations Density 0.016%

    No Known Activations