© 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. 106462
    Prev
    Next
    INDEX
    Explanations

    technical syntax and structure in programming or API documentation

    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
    ä¿
    -0.08
    utely
    -0.07
    .getRequest
    -0.07
    endency
    -0.07
    issy
    -0.07
    ÑĥÑĪ
    -0.07
    pcf
    -0.07
    ceae
    -0.07
    cth
    -0.07
    aveled
    -0.07
    POSITIVE LOGITS
     Falk
    0.06
     blank
    0.06
     JAXBElement
    0.05
    s
    0.05
    IMG
    0.05
     pall
    0.05
     com
    0.05
     ped
    0.05
    :
    0.05
     Hew
    0.05
    Activations Density 0.000%

    No Known Activations