© 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. 22-LLAMASCOPE-RES-131K
    11. 4255
    Prev
    Next
    INDEX
    Explanations

    geographical locations in Australia

    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
    931
    -0.07
    lä
    -0.06
    illas
    -0.06
    holm
    -0.06
    bra
    -0.06
    /mat
    -0.06
    langs
    -0.06
    νη
    -0.06
    eda
    -0.06
    phere
    -0.06
    POSITIVE LOGITS
    è²Į
    0.07
    /by
    0.06
    iena
    0.06
    occ
    0.06
    adoo
    0.06
    RIPT
    0.06
    íĿ
    0.06
     Bare
    0.06
     Gregg
    0.06
    opal
    0.06
    Activations Density 0.004%

    No Known Activations