© 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. 29285
    Prev
    Next
    INDEX
    Explanations

    job titles and roles in academic or research contexts

    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
    ocab
    -0.08
    oran
    -0.07
    relationships
    -0.07
    luv
    -0.07
    filt
    -0.07
    kate
    -0.07
    ungan
    -0.07
    usi
    -0.07
    usan
    -0.06
    nection
    -0.06
    POSITIVE LOGITS
     PhD
    0.07
    aland
    0.07
     Ph
    0.07
     research
    0.07
     project
    0.07
    abis
    0.06
     Research
    0.06
    442
    0.06
     leading
    0.06
    Research
    0.06
    Activations Density 0.009%

    No Known Activations