© 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. 69600
    Prev
    Next
    INDEX
    Explanations

    references to in-person interactions or events

    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
    endas
    -0.09
    AZY
    -0.09
    enda
    -0.07
    alam
    -0.07
    оÑĨÑĸ
    -0.07
    ey
    -0.07
    ospel
    -0.07
    sonian
    -0.07
    edor
    -0.07
    avian
    -0.07
    POSITIVE LOGITS
    nels
    0.07
     physical
    0.07
    nal
    0.07
    ationally
    0.06
     physically
    0.06
    397
    0.06
    ally
    0.06
    -only
    0.06
    oggle
    0.06
    496
    0.06
    Activations Density 0.003%

    No Known Activations