© 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 EvalsExportsinterp-engineNEWAPI 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. 27879
    Prev
    Next
    INDEX
    Explanations

    phrases indicating claims or assertions related to systems and processes

    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
    Ħĸ
    -0.07
    zburg
    -0.07
    adero
    -0.07
    à¥ģह
    -0.07
    unnel
    -0.07
    lover
    -0.07
    (rawValue
    -0.07
    ABCDEFGHI
    -0.06
    avers
    -0.06
    ilter
    -0.06
    POSITIVE LOGITS
     therefore
    0.34
     thus
    0.29
     consequently
    0.27
     accordingly
    0.25
     Therefore
    0.25
    thus
    0.24
     thereby
    0.24
    Therefore
    0.23
     Consequently
    0.23
     hence
    0.22
    Activations Density 0.003%

    No Known Activations