© 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. 86150
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    epy
    -0.08
    Å¡ov
    -0.07
    SELL
    -0.07
    TypeDef
    -0.07
    zag
    -0.07
    .chapter
    -0.07
    istes
    -0.07
    .Tags
    -0.07
    Ấ
    -0.07
    asil
    -0.07
    POSITIVE LOGITS
    ↵
    0.07
    :
    0.06
    row
    0.05
    Row
    0.05
    §
    0.05
    çe
    0.05
     rooftop
    0.05
    a
    0.05
    -b
    0.05
    agli
    0.05
    Activations Density 0.002%

    No Known Activations