© 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. 86566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating unavailability or access restrictions

    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
    hta
    -0.06
     unsus
    -0.06
    IGH
    -0.06
    ÃŃg
    -0.06
     laid
    -0.06
    iale
    -0.06
     pulses
    -0.06
     Licht
    -0.06
     basically
    -0.06
     flick
    -0.06
    POSITIVE LOGITS
    åı
    0.07
    ãĤĤãģĨ
    0.07
    Currently
    0.07
     ÙĦÙĩ
    0.07
    currently
    0.07
    uzzi
    0.06
    caff
    0.06
    quip
    0.06
     requested
    0.06
    falls
    0.06
    Activations Density 0.012%

    No Known Activations