© 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 EvalsExportsinterp-engineNEWAPI 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. 95802
    Prev
    Next
    INDEX
    Explanations

    the term "elsewhere" indicating content related to different locations or 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
     cái
    -0.07
    existent
    -0.07
    ernen
    -0.07
    ecut
    -0.07
    ellular
    -0.06
    ric
    -0.06
    rie
    -0.06
    set
    -0.06
    eya
    -0.06
    lite
    -0.06
    POSITIVE LOGITS
    ipple
    0.09
    _than
    0.08
    infeld
    0.08
    most
    0.07
     elsewhere
    0.07
     than
    0.07
    -than
    0.07
    tej
    0.07
    parts
    0.07
    abouts
    0.07
    Activations Density 0.003%

    No Known Activations