© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    elements related to exploration and tourism

    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
    ãģłãĤįãģĨ
    -0.07
    едж
    -0.07
    ثاÙĦ
    -0.06
    anst
    -0.06
    idad
    -0.06
    лон
    -0.06
    dic
    -0.06
    寧
    -0.06
    adr
    -0.06
    .Override
    -0.06
    POSITIVE LOGITS
     actually
    0.15
    actually
    0.12
     Actually
    0.11
     surprisingly
    0.11
    Actually
    0.10
     aslında
    0.09
     actual
    0.09
     quite
    0.09
    åħ¶å®ŀ
    0.08
    riere
    0.08
    Activations Density 0.028%

    No Known Activations