© 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. 89483
    Prev
    Next
    INDEX
    Explanations

    CSS styles related to text and color properties

    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
     dara
    -0.07
    udes
    -0.07
    hood
    -0.06
    674
    -0.06
    axon
    -0.06
    bour
    -0.06
    ictim
    -0.06
    inch
    -0.06
    imbus
    -0.06
    Binding
    -0.06
    POSITIVE LOGITS
    enville
    0.07
    piar
    0.06
    _requires
    0.06
    º«
    0.06
    lse
    0.06
    _ROUND
    0.06
    amon
    0.06
     expiresIn
    0.06
    uste
    0.06
    ponge
    0.06
    Activations Density 0.014%

    No Known Activations