© 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. 130992
    Prev
    Next
    INDEX
    Explanations

    sequences of zeros often related to error codes or 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
    ipse
    -0.07
    ãĥ¼ãĥIJ
    -0.06
    ynos
    -0.06
    spacer
    -0.06
    esktop
    -0.06
    igy
    -0.06
    oteca
    -0.06
     Anderson
    -0.06
    ecal
    -0.06
    ocus
    -0.06
    POSITIVE LOGITS
    aten
    0.07
    pgsql
    0.07
     daylight
    0.07
    çº
    0.06
    zzo
    0.06
    ãĥªãĥ¼
    0.06
    aw
    0.06
    arten
    0.06
    ufen
    0.06
    asia
    0.06
    Activations Density 0.001%

    No Known Activations