© 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. 76237
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs

    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
    Endian
    -0.08
    äre
    -0.07
    «ĺ
    -0.07
    Kansas
    -0.07
    orsi
    -0.07
     MEDIATEK
    -0.06
     CONSEQUENTIAL
    -0.06
    ownt
    -0.06
    NotFoundError
    -0.06
    otton
    -0.06
    POSITIVE LOGITS
     Furn
    0.07
    iman
    0.07
     ES
    0.06
     Cluster
    0.06
     TNT
    0.06
    onga
    0.06
     kim
    0.06
    ixa
    0.06
    815
    0.06
    386
    0.06
    Activations Density 0.069%

    No Known Activations