© 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. 121032
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities for education and sponsorship

    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
     ucwords
    -0.07
    uros
    -0.07
    iri
    -0.06
     Flesh
    -0.06
    urus
    -0.06
    ãĤ¤ãĥĪ
    -0.06
    yet
    -0.06
    orman
    -0.06
     Arte
    -0.06
    icken
    -0.05
    POSITIVE LOGITS
    uhl
    0.07
    λά
    0.06
    lag
    0.06
     spol
    0.06
    FRING
    0.06
    adden
    0.06
    ieber
    0.06
    lep
    0.06
    intValue
    0.06
    kes
    0.06
    Activations Density 0.023%

    No Known Activations