© 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. 17-LLAMASCOPE-RES-131K
    11. 75962
    Prev
    Next
    INDEX
    Explanations

    numerical sequences or time indicators such as timestamps

    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
    jeme
    -0.06
    uman
    -0.06
     Woody
    -0.06
    вол
    -0.06
    olars
    -0.05
    неÑĤ
    -0.05
     New
    -0.05
    CodeGen
    -0.05
     ar
    -0.05
     Man
    -0.05
    POSITIVE LOGITS
    una
    0.07
    ikon
    0.07
    orden
    0.07
    hq
    0.07
    ÏĩεδÏĮν
    0.07
    steen
    0.07
     æ¥Ń
    0.07
    _IMPLEMENT
    0.06
    галÑĸ
    0.06
     ìłĦ
    0.06
    Activations Density 0.003%

    No Known Activations