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. 11489
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
     colourful
    -0.06
     disap
    -0.06
     neighbour
    -0.06
     vÄĽ
    -0.06
    DNS
    -0.06
     defence
    -0.06
     batt
    -0.06
     simd
    -0.06
    etty
    -0.05
     Cyan
    -0.05
    POSITIVE LOGITS
     rehab
    0.17
     rehabilitation
    0.16
     drug
    0.14
     alcohol
    0.13
     Rehabilitation
    0.13
     Drug
    0.13
     Rehab
    0.12
     detox
    0.12
     treatment
    0.12
     substance
    0.12
    Activations Density 0.002%

    No Known Activations