© 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. 55063
    Prev
    Next
    INDEX
    Explanations

    references to individual artists and their works

    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
     Brow
    -0.07
    urr
    -0.07
    itted
    -0.06
     steps
    -0.06
     removable
    -0.05
    ovit
    -0.05
    -cols
    -0.05
     pledges
    -0.05
    arsers
    -0.05
     aspects
    -0.05
    POSITIVE LOGITS
    pok
    0.08
    اض
    0.07
    ibble
    0.07
    _ASSUME
    0.07
    FLAGS
    0.07
    ucher
    0.07
    ghi
    0.07
    InRange
    0.07
    vÃŃc
    0.07
    cca
    0.07
    Activations Density 0.027%

    No Known Activations