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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5141
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to user interface design and web development

    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
    uele
    -0.08
    erli
    -0.08
    cljs
    -0.08
    ç´ł
    -0.07
    abela
    -0.07
    ormal
    -0.07
    alez
    -0.07
    ootball
    -0.07
    crets
    -0.07
    zig
    -0.07
    POSITIVE LOGITS
     yes
    0.06
    adr
    0.06
     squash
    0.06
    ivery
    0.06
     IT
    0.06
    =no
    0.06
     Taylor
    0.06
    373
    0.06
     mixed
    0.05
     no
    0.05
    Activations Density 0.001%

    No Known Activations