© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126746
    Prev
    Next
    INDEX
    Explanations

    instances of win-lose scenarios or win-win agreements

    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
    ALLE
    -0.07
    olle
    -0.06
    _DESTROY
    -0.06
    uo
    -0.06
    uppe
    -0.06
    alle
    -0.06
    473
    -0.06
    872
    -0.06
    aÅŁ
    -0.06
    çε
    -0.05
    POSITIVE LOGITS
    /stretch
    0.08
    CallCheck
    0.07
    GREEN
    0.07
    iesen
    0.07
    ruz
    0.07
    etu
    0.07
    nable
    0.07
    etooth
    0.07
    raq
    0.07
    pter
    0.06
    Activations Density 0.001%

    No Known Activations