© 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. 15-LLAMASCOPE-RES-131K
    6. 62077
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, specifically related to North and South

    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
    coni
    -0.10
    ously
    -0.08
    itious
    -0.07
    oom
    -0.07
    atur
    -0.07
    ature
    -0.07
    lect
    -0.07
    istence
    -0.07
    encer
    -0.07
    ÏĢοÏĦε
    -0.07
    POSITIVE LOGITS
    ward
    0.10
    western
    0.09
    side
    0.08
    umberland
    0.08
     tiên
    0.08
    bound
    0.08
    wick
    0.08
    üzel
    0.07
    cott
    0.07
    -west
    0.07
    Activations Density 0.048%

    No Known Activations