© 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. 130962
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Reuters" in the text

    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
    regs
    -0.07
    owski
    -0.07
    blings
    -0.07
    tek
    -0.06
    sc
    -0.06
    sWith
    -0.06
    abella
    -0.06
    abyrin
    -0.06
    side
    -0.06
    gs
    -0.06
    POSITIVE LOGITS
    entes
    0.07
    zyst
    0.07
    iam
    0.07
    ï¸
    0.07
    .AutoComplete
    0.07
    ÃĴ
    0.06
    iná
    0.06
     latter
    0.06
    onec
    0.06
    _SELF
    0.06
    Activations Density 0.003%

    No Known Activations