© 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. 15-LLAMASCOPE-RES-131K
    11. 89469
    Prev
    Next
    INDEX
    Explanations

    invitations or suggestions to participate in activities

    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
    ilda
    -0.08
    oa
    -0.07
    ãĥ¼ãĤ¸
    -0.06
    ngr
    -0.06
    orado
    -0.06
    udson
    -0.06
    ema
    -0.06
     separ
    -0.06
    ogo
    -0.06
     crude
    -0.06
    POSITIVE LOGITS
     start
    0.09
     START
    0.08
     missed
    0.08
    $start
    0.07
     skipping
    0.07
    ä»ĭ
    0.07
     starting
    0.07
     late
    0.07
    -start
    0.07
    (start
    0.07
    Activations Density 0.099%

    No Known Activations