© 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. 119056
    Prev
    Next
    INDEX
    Explanations

    references to geometric shapes and arrangements

    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
    iah
    -0.07
    agger
    -0.06
    ologne
    -0.06
    forth
    -0.06
    ilter
    -0.06
    ÙĪبÛĮ
    -0.06
    rve
    -0.06
     пÑĢиз
    -0.06
    arez
    -0.06
     Cube
    -0.06
    POSITIVE LOGITS
     rings
    0.15
     ring
    0.15
     Ring
    0.14
    -ring
    0.13
    Ring
    0.12
     outer
    0.12
     circum
    0.12
    çݯ
    0.11
     circle
    0.11
     Rings
    0.11
    Activations Density 0.071%

    No Known Activations