Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119217
    Prev
    Next
    INDEX
    Explanations

    technical configuration options related to a system or software

    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
    CardBody
    -0.07
    aller
    -0.07
    à¹Ģห
    -0.06
    ownt
    -0.06
    esen
    -0.06
    athed
    -0.06
    ISR
    -0.06
    ìŰ
    -0.06
    >(()
    -0.06
    θÏħ
    -0.06
    POSITIVE LOGITS
    ui
    0.08
    isch
    0.07
     Yard
    0.06
    ucha
    0.06
     Nicholson
    0.06
    NSURLSession
    0.06
    -hash
    0.06
     mặt
    0.06
     amnesty
    0.06
    616
    0.06
    Activations Density 0.015%

    No Known Activations