© 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. 41721
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to products

    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
    obile
    -0.07
    Ñĸж
    -0.07
    .createClass
    -0.07
    EMPLARY
    -0.07
    inson
    -0.07
    оваÑĢ
    -0.07
    .createFrom
    -0.07
    ADATA
    -0.07
    lage
    -0.07
    è·
    -0.07
    POSITIVE LOGITS
     pub
    0.07
     manifest
    0.07
    lal
    0.06
     Bundes
    0.06
     Part
    0.06
    175
    0.06
    sov
    0.06
    IFEST
    0.06
     bare
    0.06
    iad
    0.06
    Activations Density 0.004%

    No Known Activations