© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26404
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with notable individuals

    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
    ̧
    -0.07
     a
    -0.06
     Wy
    -0.06
    Ìģt
    -0.06
     putas
    -0.06
    ÌĤ
    -0.06
    .mc
    -0.06
    onth
    -0.06
    áº
    -0.06
     Leigh
    -0.06
    POSITIVE LOGITS
    324
    0.07
    washer
    0.07
    ħn
    0.07
    icipant
    0.07
    ewise
    0.07
    UILTIN
    0.07
    .setViewport
    0.06
    ignal
    0.06
    roc
    0.06
    elijk
    0.06
    Activations Density 0.033%

    No Known Activations