© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123411
    Prev
    Next
    INDEX
    Explanations

    distinctions between locals and visitors, as well as identifying the features of real versus fake fur

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rok
    -0.07
     plá
    -0.07
    imax
    -0.07
    amient
    -0.07
    adow
    -0.06
    lum
    -0.06
    amerate
    -0.06
     fluids
    -0.06
    orum
    -0.06
    orsi
    -0.06
    POSITIVE LOGITS
     usually
    0.09
     generally
    0.09
     typically
    0.09
    usually
    0.08
     characteristics
    0.08
     Usually
    0.08
    typically
    0.07
    gener
    0.07
     обÑĭÑĩно
    0.07
     easily
    0.07
    Activations Density 0.034%

    No Known Activations