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. 60923
    Prev
    Next
    INDEX
    Explanations

    patterns of comparison or contrast

    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
    EMPLARY
    -0.08
    loor
    -0.08
    ksen
    -0.07
    acman
    -0.07
    lew
    -0.07
    oller
    -0.07
    enga
    -0.07
    ERO
    -0.07
    ÑĢоÑĪ
    -0.07
    ospace
    -0.06
    POSITIVE LOGITS
     vice
    0.46
     Vice
    0.37
    vice
    0.35
     reverse
    0.32
     Conversely
    0.28
     converse
    0.27
    reverse
    0.27
     opposite
    0.27
     Reverse
    0.26
    Reverse
    0.25
    Activations Density 0.165%

    No Known Activations