© 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. 130845
    Prev
    Next
    INDEX
    Explanations

    mentions of new or updated content across various topics or media

    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
    лова
    -0.08
    ommen
    -0.07
    ogh
    -0.07
    oble
    -0.06
    rowse
    -0.06
    VOKE
    -0.06
    defense
    -0.06
    úc
    -0.06
    á»įt
    -0.06
     Woche
    -0.06
    POSITIVE LOGITS
    sp
    0.07
    ichert
    0.07
     addition
    0.06
    urst
    0.06
    alla
    0.06
    Å¡en
    0.06
    chez
    0.06
     twists
    0.06
     version
    0.06
    -to
    0.06
    Activations Density 0.012%

    No Known Activations