© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 106969
    Prev
    Next
    INDEX
    Explanations

    references to candy and chocolate products

    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
     Cable
    -0.06
    rous
    -0.06
    alfa
    -0.06
     Blade
    -0.06
     Poz
    -0.06
    419
    -0.06
    acock
    -0.06
     Blades
    -0.06
     Vine
    -0.06
     dishes
    -0.06
    POSITIVE LOGITS
    à¸ŀระราà¸Ĭ
    0.07
     bars
    0.07
     crem
    0.07
    åĿļ
    0.07
     automát
    0.07
     aisle
    0.07
     glac
    0.07
     unpack
    0.07
    pret
    0.06
    \Backend
    0.06
    Activations Density 0.025%

    No Known Activations