© 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. 17-LLAMASCOPE-RES-131K
    11. 84703
    Prev
    Next
    INDEX
    Explanations

    information related to academic qualifications and student requirements

    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
    jerne
    -0.07
    auge
    -0.07
    zas
    -0.07
    ấu
    -0.07
    ofi
    -0.06
    idunt
    -0.06
     dash
    -0.06
    rof
    -0.06
     гла
    -0.06
    ủng
    -0.06
    POSITIVE LOGITS
    ymb
    0.07
    inis
    0.07
     already
    0.07
    778
    0.07
    mot
    0.06
    ">#
    0.06
    _splits
    0.06
     interest
    0.06
    transfer
    0.06
     Clients
    0.06
    Activations Density 0.019%

    No Known Activations