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. 43439
    Prev
    Next
    INDEX
    Explanations

    references to game mechanics and parameters

    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
    BSD
    -0.06
    astype
    -0.06
    parison
    -0.06
     δο
    -0.06
    atas
    -0.06
    æ¢ģ
    -0.06
    verter
    -0.06
     pillow
    -0.05
     showc
    -0.05
     headset
    -0.05
    POSITIVE LOGITS
     movement
    0.12
     Initiative
    0.12
     turn
    0.11
     Movement
    0.11
     initiative
    0.11
     turns
    0.10
    Movement
    0.10
     Turn
    0.10
     move
    0.10
     phase
    0.10
    Activations Density 0.007%

    No Known Activations