© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40138
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to locations and geography

    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
    /or
    -0.06
    assi
    -0.06
     (
    -0.06
    ...↵
    -0.06
     rip
    -0.06
     Humph
    -0.06
    -less
    -0.06
    (the
    -0.05
     different
    -0.05
    /high
    -0.05
    POSITIVE LOGITS
    inu
    0.08
     stesso
    0.08
     ÙĨÙģسÙĩ
    0.08
    ymax
    0.08
     Hentai
    0.07
    adem
    0.07
    agal
    0.07
    że
    0.07
    InParameter
    0.07
    orado
    0.07
    Activations Density 0.027%

    No Known Activations