© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27008
    Prev
    Next
    INDEX
    Explanations

    references to stock performance and market viability

    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
    esis
    -0.07
    éĬ
    -0.07
    angan
    -0.07
    lex
    -0.06
    _FAILURE
    -0.06
     Stam
    -0.06
    _clause
    -0.06
    idders
    -0.06
    nett
    -0.06
    eb
    -0.06
    POSITIVE LOGITS
     lately
    0.07
    лиÑĨ
    0.06
    uitka
    0.06
     recent
    0.06
     cyclic
    0.06
     trú
    0.06
    omo
    0.06
     Sab
    0.06
    uba
    0.06
     recently
    0.06
    Activations Density 0.009%

    No Known Activations