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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40393
    Prev
    Next
    INDEX
    Explanations

    instructions related to tasks that require immediate attention or organization

    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
    å´İ
    -0.07
     شعر
    -0.07
    697
    -0.07
    à¥ģण
    -0.07
    ricks
    -0.07
     Glover
    -0.06
    yne
    -0.06
    iqué
    -0.06
    æ´¥
    -0.06
     fewer
    -0.06
    POSITIVE LOGITS
    æīįèĥ½
    0.08
    155
    0.06
    æīį
    0.06
    aires
    0.06
    plat
    0.06
     Fly
    0.06
     Pell
    0.06
    amas
    0.06
     inorder
    0.06
     Tin
    0.06
    Activations Density 0.020%

    No Known Activations