© 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. 76357
    Prev
    Next
    INDEX
    Explanations

    structured programming syntax elements

    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
    owie
    -0.06
    umin
    -0.06
    ideographic
    -0.06
    ÑĢади
    -0.06
    utos
    -0.06
    puty
    -0.06
    amburger
    -0.06
    ©©
    -0.06
    adiens
    -0.06
    ensity
    -0.06
    POSITIVE LOGITS
    ÄĻp
    0.07
    cers
    0.06
    åĬ
    0.06
     Pearson
    0.06
    emek
    0.06
    cer
    0.06
    à¹ĥà¸Ī
    0.06
    677
    0.06
    380
    0.06
     Nack
    0.06
    Activations Density 0.047%

    No Known Activations