Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16366
    Prev
    Next
    INDEX
    Explanations

    mentions of sports and related media content

    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
    arra
    -0.07
    indh
    -0.07
    ansa
    -0.06
    ante
    -0.06
    kol
    -0.06
     televised
    -0.06
    åŀ
    -0.06
     televizyon
    -0.06
    .comp
    -0.06
    à¸Ĺะ
    -0.06
    POSITIVE LOGITS
    åĴ²
    0.07
     Anc
    0.07
     anc
    0.07
    AUSE
    0.06
    аÑĢÑħ
    0.06
     Archie
    0.06
    Archive
    0.06
    etz
    0.06
     Archives
    0.06
     archives
    0.06
    Activations Density 0.081%

    No Known Activations