© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61124
    Prev
    Next
    INDEX
    Explanations

    instances of breaks or transitions in text, possibly related to formatting or section headings

    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
    ifer
    -0.07
    anton
    -0.06
    izi
    -0.06
    stå
    -0.06
    ÅĻÃŃzenÃŃ
    -0.06
    stri
    -0.06
    ocket
    -0.06
    ilden
    -0.06
     ì¹ľ
    -0.06
     Flags
    -0.06
    POSITIVE LOGITS
    ê³
    0.07
    arp
    0.06
    uhan
    0.06
    LETE
    0.06
     Toro
    0.06
    owan
    0.06
     Gomez
    0.06
    ìĿĮìĿĦ
    0.06
     Walsh
    0.06
    ejs
    0.06
    Activations Density 0.000%

    No Known Activations