© 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. 247
    Prev
    Next
    INDEX
    Explanations

    discourse markers and references to logical transitions or conditions

    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
    oppins
    -0.08
    allo
    -0.08
    ako
    -0.07
    oya
    -0.07
    usterity
    -0.07
    alo
    -0.07
    ammers
    -0.07
    voÅĻ
    -0.06
    amar
    -0.06
    ao
    -0.06
    POSITIVE LOGITS
    ży
    0.06
    íİ
    0.06
     sa
    0.06
     Dana
    0.06
    _scope
    0.06
    Fo
    0.06
    plen
    0.05
     اÙĦÙĬ
    0.05
     Fate
    0.05
    HRESULT
    0.05
    Activations Density 0.040%

    No Known Activations