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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11514
    Prev
    Next
    INDEX
    Explanations

    references to additional media content and updates related to television shows

    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
    alsa
    -0.06
    دا
    -0.06
    Intro
    -0.06
    uges
    -0.06
    çIJĨ
    -0.06
    CrLf
    -0.06
    ç¹ģ
    -0.06
    resas
    -0.06
     æ¼Ķ
    -0.06
    .sourceforge
    -0.06
    POSITIVE LOGITS
     coverage
    0.16
     updates
    0.15
     news
    0.14
     info
    0.13
     content
    0.13
     insight
    0.13
     intel
    0.13
     information
    0.13
    coverage
    0.12
     insights
    0.12
    Activations Density 0.044%

    No Known Activations