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. 22-LLAMASCOPE-RES-131K
    6. 5717
    Prev
    Next
    INDEX
    Explanations

    achievements related to space exploration and aviation

    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
    tru
    -0.07
    anca
    -0.07
    agate
    -0.06
     haus
    -0.06
     cluster
    -0.06
     nat
    -0.06
    alfa
    -0.06
    âĹİ
    -0.05
    lsa
    -0.05
    ayd
    -0.05
    POSITIVE LOGITS
     Crew
    0.13
     astronaut
    0.13
     crew
    0.13
     astronauts
    0.12
    onaut
    0.12
     Space
    0.12
     mission
    0.11
     Shuttle
    0.11
    Space
    0.11
     Soy
    0.11
    Activations Density 0.068%

    No Known Activations