© 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. 39814
    Prev
    Next
    INDEX
    Explanations

    elements related to list formatting in documents

    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
    óc
    -0.08
    zing
    -0.07
    OLEAN
    -0.07
    ATEST
    -0.07
    readcr
    -0.07
    innacle
    -0.07
    eldon
    -0.06
    ÏĨÏħ
    -0.06
    opes
    -0.06
    arme
    -0.06
    POSITIVE LOGITS
    oman
    0.07
    åľ
    0.06
     Cas
    0.06
    638
    0.06
     przypad
    0.06
    SG
    0.06
    yt
    0.06
    iel
    0.06
     cas
    0.05
     Continue
    0.05
    Activations Density 0.014%

    No Known Activations