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

    Neuronpedia

    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. 17144
    Prev
    Next
    INDEX
    Explanations

    features and benefits of technology or methodologies

    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
     addCriterion
    -0.09
    ÙĪاء
    -0.06
     PRES
    -0.06
    uzey
    -0.06
    azaar
    -0.06
    resar
    -0.06
    iji
    -0.06
    vier
    -0.06
    undle
    -0.06
    (crate
    -0.06
    POSITIVE LOGITS
    使
    0.09
     makes
    0.09
    makes
    0.09
    earning
    0.09
     earning
    0.08
     Makes
    0.08
    make
    0.08
     hence
    0.07
     appeal
    0.07
     appeals
    0.07
    Activations Density 0.054%

    No Known Activations