© 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. 62755
    Prev
    Next
    INDEX
    Explanations

    numerical values and figures related to products or items

    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
    ello
    -0.08
    mas
    -0.08
    rons
    -0.07
    lock
    -0.07
    arel
    -0.06
    men
    -0.06
    iny
    -0.06
    als
    -0.06
    alse
    -0.06
    маз
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    Rare
    0.07
    UIAlertView
    0.07
    strcasecmp
    0.07
    aska
    0.07
    Gratis
    0.06
    /chart
    0.06
    .channels
    0.06
    PLOY
    0.06
    siz
    0.06
    Activations Density 0.010%

    No Known Activations