© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85923
    Prev
    Next
    INDEX
    Explanations

    references to pioneering contributions in writing and design

    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
    dna
    -0.07
    icas
    -0.07
    appiness
    -0.06
    ån
    -0.06
    ica
    -0.06
    átis
    -0.06
    mut
    -0.06
    exec
    -0.06
    éf
    -0.06
     Claw
    -0.06
    POSITIVE LOGITS
     magazine
    0.08
     analyst
    0.08
    gon
    0.08
     scre
    0.08
     reviews
    0.08
     coverage
    0.08
     Analyst
    0.07
     columns
    0.07
     Reviews
    0.07
     reviewing
    0.07
    Activations Density 0.014%

    No Known Activations