© 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. 93802
    Prev
    Next
    INDEX
    Explanations

    references to the "Odyssey," indicating a focus on themes related to journey or adventure

    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
    feit
    -0.07
    Ø®ÙĪ
    -0.07
    urer
    -0.07
    aeda
    -0.07
    oleÄį
    -0.07
    иж
    -0.07
    uhn
    -0.07
    igm
    -0.07
    ocumented
    -0.06
    리ì§Ģ
    -0.06
    POSITIVE LOGITS
    yssey
    0.10
    mium
    0.07
    ball
    0.07
    ding
    0.07
    obo
    0.06
    iber
    0.06
    pend
    0.06
    wald
    0.06
     strang
    0.06
    erno
    0.06
    Activations Density 0.011%

    No Known Activations