© 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. 88084
    Prev
    Next
    INDEX
    Explanations

    references to data collection and experimental procedures

    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
    .gdx
    -0.08
    artner
    -0.08
    jectory
    -0.07
    patterns
    -0.07
    ï¼ģ”↵↵
    -0.07
    (=)
    -0.07
    ibri
    -0.07
    mium
    -0.07
    .nlm
    -0.07
    chten
    -0.07
    POSITIVE LOGITS
     continued
    0.07
     continuing
    0.07
     mock
    0.07
     implement
    0.06
     ready
    0.06
     develop
    0.06
     prepare
    0.06
     interf
    0.06
     continue
    0.06
     continues
    0.06
    Activations Density 0.005%

    No Known Activations