© 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. 9-LLAMASCOPE-RES-131K
    11. 99287
    Prev
    Next
    INDEX
    Explanations

    identifiers related to inventory and product listings

    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
    ather
    -0.07
     subdiv
    -0.06
    aña
    -0.06
    ille
    -0.06
    h
    -0.06
     quit
    -0.06
    uir
    -0.06
    ni
    -0.06
    uo
    -0.06
    oad
    -0.06
    POSITIVE LOGITS
    lád
    0.08
    iously
    0.07
    ipi
    0.07
    uffman
    0.07
    ious
    0.07
    icontrol
    0.07
    erator
    0.07
    isÃŃ
    0.07
    infos
    0.07
    ittest
    0.07
    Activations Density 0.002%

    No Known Activations