© 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. 5-LLAMASCOPE-RES-131K
    11. 126696
    Prev
    Next
    INDEX
    Explanations

    educational qualifications and degrees

    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
    oose
    -0.06
    ropic
    -0.06
     Penal
    -0.06
    ylko
    -0.06
     Penalty
    -0.06
    .windows
    -0.06
    ansi
    -0.06
     Beste
    -0.06
    uga
    -0.06
    ç¯
    -0.06
    POSITIVE LOGITS
    asin
    0.07
     Hick
    0.07
     russ
    0.06
    uder
    0.06
     Weiner
    0.06
    aml
    0.06
    ennen
    0.06
     nod
    0.06
     degree
    0.06
    ůst
    0.06
    Activations Density 0.474%

    No Known Activations