© 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 EvalsExportsAPI 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. 89050
    Prev
    Next
    INDEX
    Explanations

    punctuated lists and references within academic texts

    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
    @student
    -0.08
    achs
    -0.08
    Ø
    -0.07
    Ef
    -0.07
    aminer
    -0.07
    ìŀ¬
    -0.07
    adf
    -0.06
    urgeon
    -0.06
     dangling
    -0.06
    rage
    -0.06
    POSITIVE LOGITS
     volume
    0.08
     vol
    0.07
    isser
    0.07
    ecz
    0.06
     Volume
    0.06
    esar
    0.06
     Vol
    0.06
     volumes
    0.06
     peer
    0.06
    407
    0.06
    Activations Density 0.000%

    No Known Activations