© 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. 17-LLAMASCOPE-RES-131K
    11. 107162
    Prev
    Next
    INDEX
    Explanations

    the word "across" in various 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
    ulin
    -0.09
    kenin
    -0.08
    ls
    -0.07
    cken
    -0.07
    kest
    -0.07
    och
    -0.07
    áºŃt
    -0.07
    thing
    -0.07
    mie
    -0.07
    ÑĮко
    -0.07
    POSITIVE LOGITS
    -the
    0.10
    s
    0.08
    enger
    0.07
    sar
    0.07
    ader
    0.07
    cut
    0.07
    fade
    0.07
    /down
    0.07
     spectrum
    0.07
    /in
    0.07
    Activations Density 0.019%

    No Known Activations