© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61707
    Prev
    Next
    INDEX
    Explanations

    words signaling excess or additional feelings and experiences

    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
    ιαÏĤ
    -0.07
    สมà¸ļ
    -0.06
    bots
    -0.06
    isoft
    -0.06
    زد
    -0.06
    arrera
    -0.06
    ä¹Łæľī
    -0.06
    /loose
    -0.06
    Founded
    -0.06
    ARB
    -0.06
    POSITIVE LOGITS
    ivery
    0.07
    cko
    0.07
    ragon
    0.06
     manner
    0.06
    ipples
    0.06
    GI
    0.06
    ague
    0.06
    ckett
    0.06
    cket
    0.06
     somehow
    0.06
    Activations Density 0.019%

    No Known Activations