© 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. 118570
    Prev
    Next
    INDEX
    Explanations

    structured sentences and punctuation in the context of a review or commentary

    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
    tings
    -0.08
    zburg
    -0.07
     ci
    -0.07
    째
    -0.07
    ulings
    -0.07
    ypse
    -0.07
    ters
    -0.07
    addock
    -0.07
    IFT
    -0.06
    åºŃ
    -0.06
    POSITIVE LOGITS
     VIR
    0.07
     nails
    0.06
    325
    0.06
    ricks
    0.06
    amp
    0.06
    modifiable
    0.06
     reproduction
    0.06
    oq
    0.06
     Nail
    0.06
    oad
    0.06
    Activations Density 0.005%

    No Known Activations