© 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. 75676
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large quantity or extensive range

    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
    串
    -0.07
    ear
    -0.07
     konce
    -0.07
    /package
    -0.06
     Verfüg
    -0.06
    EDIA
    -0.06
    713
    -0.06
    icontains
    -0.06
    ÏĦεί
    -0.06
    áp
    -0.06
    POSITIVE LOGITS
     dozens
    0.10
     hundreds
    0.09
     thousands
    0.08
    zens
    0.07
     dozen
    0.07
     Hundreds
    0.07
    ientos
    0.06
     tens
    0.06
    ff
    0.06
    orraine
    0.06
    Activations Density 0.020%

    No Known Activations