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. 125624
    Prev
    Next
    INDEX
    Explanations

    references to winter

    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
    elaide
    -0.07
    vara
    -0.07
    WithValue
    -0.07
    .scalablytyped
    -0.07
    usc
    -0.07
    iap
    -0.07
    egot
    -0.07
    ek
    -0.07
    ais
    -0.07
    inosaur
    -0.07
    POSITIVE LOGITS
    thur
    0.09
    -time
    0.08
     wonder
    0.08
    mute
    0.08
    ime
    0.08
    green
    0.08
     break
    0.07
     months
    0.07
    lude
    0.07
    semester
    0.07
    Activations Density 0.008%

    No Known Activations