© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78168
    Prev
    Next
    INDEX
    Explanations

    references to specific sections in a document

    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
    ighton
    -0.07
    kit
    -0.07
    ÐĤ
    -0.06
    cai
    -0.06
    inkle
    -0.06
     Verfügung
    -0.06
    ONEY
    -0.06
     Bien
    -0.06
    moth
    -0.06
    大åħ¨
    -0.06
    POSITIVE LOGITS
    (section
    0.07
    @section
    0.07
    sWith
    0.06
    .section
    0.06
     subsection
    0.06
    ahas
    0.06
    reira
    0.06
    ennen
    0.06
     section
    0.06
    disposing
    0.06
    Activations Density 0.022%

    No Known Activations