© 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. 15-LLAMASCOPE-RES-131K
    11. 90776
    Prev
    Next
    INDEX
    Explanations

    patterns related to changes and conditions in scientific processes and measurements

    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
    /GPL
    -0.08
    utsch
    -0.07
    stdClass
    -0.07
    amp
    -0.07
    anker
    -0.07
    anium
    -0.06
    /cgi
    -0.06
    iesen
    -0.06
    eneg
    -0.06
    tright
    -0.06
    POSITIVE LOGITS
    è¶Ĭ
    0.07
    elters
    0.07
     cÃłng
    0.06
     increases
    0.06
    rophe
    0.06
    EO
    0.06
     increased
    0.06
     Swe
    0.06
    nock
    0.06
     age
    0.06
    Activations Density 0.030%

    No Known Activations