© 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. 125645
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "by" indicating authorship or agency

    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
    olini
    -0.09
    код
    -0.08
     ç¯
    -0.08
     tisk
    -0.08
    rlen
    -0.07
     ков
    -0.07
    gba
    -0.07
    imits
    -0.07
    arith
    -0.07
    aghan
    -0.07
    POSITIVE LOGITS
     powered
    0.06
     powerful
    0.06
     Browse
    0.06
     technology
    0.06
     powers
    0.06
     ideas
    0.06
    -powered
    0.06
     strong
    0.06
     differential
    0.06
    486
    0.06
    Activations Density 0.005%

    No Known Activations