© 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. 106332
    Prev
    Next
    INDEX
    Explanations

    names of people associated with newsworthy events or subjects

    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
    .html
    -0.07
    ecer
    -0.06
     Pdf
    -0.06
    Foot
    -0.06
    emain
    -0.06
    adal
    -0.06
    cene
    -0.06
     oversh
    -0.06
     reservations
    -0.06
    sg
    -0.06
    POSITIVE LOGITS
    /Getty
    0.10
    UTERS
    0.08
    /AFP
    0.08
     Wikimedia
    0.08
     stock
    0.08
    utterstock
    0.08
    -stock
    0.08
     stocks
    0.07
     Stocks
    0.07
     ì´
    0.07
    Activations Density 0.031%

    No Known Activations