© 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. 83808
    Prev
    Next
    INDEX
    Explanations

    terms related to health and safety concerns

    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
    azz
    -0.07
    aires
    -0.07
    uest
    -0.06
    mare
    -0.06
    micro
    -0.06
    esda
    -0.06
    ablo
    -0.06
     itself
    -0.06
    ãĤĪãĤĬãĤĤ
    -0.06
    elta
    -0.06
    POSITIVE LOGITS
     exists
    0.08
    olia
    0.07
     accompanies
    0.07
    lots
    0.07
    Same
    0.06
    olian
    0.06
     existed
    0.06
    419
    0.06
     involved
    0.06
    zeich
    0.06
    Activations Density 0.137%

    No Known Activations