© 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. 127128
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "at least."

    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
    itzer
    -0.07
     TimeUnit
    -0.07
    rez
    -0.07
    à¸ĩà¸Ļ
    -0.07
     apenas
    -0.07
    er
    -0.06
    ãģªãĤĵãģ¦
    -0.06
    ast
    -0.06
    ounty
    -0.06
     hanya
    -0.06
    POSITIVE LOGITS
     partially
    0.08
     partly
    0.08
    908
    0.07
     partial
    0.07
    ä¹ĭä¸Ģ
    0.07
     Partial
    0.06
    odos
    0.06
    some
    0.06
     Rich
    0.06
    som
    0.06
    Activations Density 0.020%

    No Known Activations