© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56772
    Prev
    Next
    INDEX
    Explanations

    expressions of the present or ongoing events

    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
     should
    -0.07
     or
    -0.07
    ÑĢаж
    -0.07
    /
    -0.07
    should
    -0.06
     ought
    -0.06
    ,
    -0.06
    heimer
    -0.06
    or
    -0.06
    r
    -0.06
    POSITIVE LOGITS
     seedu
    0.08
     Currently
    0.07
    ãģĹãģĭ
    0.07
    oÄŁ
    0.07
    Currently
    0.07
    kaar
    0.07
    OLEAN
    0.07
    urlencode
    0.07
    @nate
    0.06
    кÑĥлÑĮ
    0.06
    Activations Density 0.008%

    No Known Activations