© 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. 128582
    Prev
    Next
    INDEX
    Explanations

    place names and geographic features

    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
    ĵn
    -0.07
    _FP
    -0.07
    intl
    -0.07
    (åľŁ
    -0.07
    udson
    -0.06
    .named
    -0.06
    .sourceforge
    -0.06
     поба
    -0.06
    _exports
    -0.06
    amburger
    -0.06
    POSITIVE LOGITS
     itself
    0.08
     Upper
    0.07
    ilde
    0.07
    ensis
    0.07
     village
    0.07
    -area
    0.06
    -centered
    0.06
    oto
    0.06
    amba
    0.06
    uctions
    0.06
    Activations Density 0.015%

    No Known Activations