Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126168
    Prev
    Next
    INDEX
    Explanations

    references to financial performance and sales figures in the gaming industry

    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
    icap
    -0.06
    nerRadius
    -0.06
    iswa
    -0.06
    åºŁ
    -0.06
    fsp
    -0.06
    rowse
    -0.06
    urst
    -0.06
    gence
    -0.05
    æĸ
    -0.05
    utt
    -0.05
    POSITIVE LOGITS
     -*-č↵
    0.07
     -------------------------------------------------------------------------
    0.07
    -toggler
    0.07
    еÑĢап
    0.06
     postav
    0.06
     desar
    0.06
    ython
    0.06
    ãĥ¼ãĥĢ
    0.06
     Leban
    0.06
    δεÏĤ
    0.06
    Activations Density 0.053%

    No Known Activations