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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4723
    Prev
    Next
    INDEX
    Explanations

    testimonials highlighting the quality of service and professionalism

    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
    kate
    -0.06
    Tomorrow
    -0.06
    lád
    -0.06
    kowski
    -0.06
    ór
    -0.06
    ynes
    -0.06
     according
    -0.06
    aeper
    -0.06
    mtree
    -0.06
     tomorrow
    -0.06
    POSITIVE LOGITS
     communication
    0.10
     Communication
    0.09
    arie
    0.09
    communication
    0.08
     komunik
    0.08
     communications
    0.08
     Communications
    0.08
    æ²Ł
    0.07
     communic
    0.07
    Communication
    0.07
    Activations Density 0.028%

    No Known Activations