© 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. 105380
    Prev
    Next
    INDEX
    Explanations

    references to comic book franchises and related lists

    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
     excess
    -0.06
     tune
    -0.06
     nationally
    -0.06
     Raq
    -0.06
    _iff
    -0.06
    UCE
    -0.06
     Myst
    -0.05
    force
    -0.05
     FORCE
    -0.05
    .WebControls
    -0.05
    POSITIVE LOGITS
     chron
    0.09
    chron
    0.09
     chronological
    0.08
     поÑĢÑıдке
    0.08
    recommended
    0.07
    /INFO
    0.07
    assertCount
    0.07
     sequ
    0.07
    addon
    0.07
     binge
    0.07
    Activations Density 0.002%

    No Known Activations