© 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. 93087
    Prev
    Next
    INDEX
    Explanations

    instances of being behind or delayed in progress compared to peers or standards

    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
    eric
    -0.07
    fx
    -0.07
    oldem
    -0.07
    oud
    -0.07
     ServletException
    -0.07
    ामन
    -0.06
    vio
    -0.06
    umo
    -0.06
    uo
    -0.06
    à¹Īย
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
    íĥĢ
    0.07
    Others
    0.07
    afe
    0.07
     others
    0.06
    middlewares
    0.06
    å¢
    0.06
    angl
    0.06
    TEGER
    0.06
     schedule
    0.06
    Activations Density 0.010%

    No Known Activations