© 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. 9-LLAMASCOPE-RES-131K
    11. 97762
    Prev
    Next
    INDEX
    Explanations

    percentage and statistical data points in context

    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
    imitives
    -0.08
    lot
    -0.07
    СÐŀ
    -0.07
    (EXPR
    -0.07
     Salisbury
    -0.06
    μοÏħ
    -0.06
     Yours
    -0.06
    tering
    -0.06
    OrDefault
    -0.06
    AMA
    -0.06
    POSITIVE LOGITS
    oret
    0.07
    ackets
    0.06
    isco
    0.06
    UnitTest
    0.06
    ambah
    0.06
    arpa
    0.06
    adel
    0.05
     Band
    0.05
    iscal
    0.05
    arge
    0.05
    Activations Density 0.156%

    No Known Activations