© 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. 95885
    Prev
    Next
    INDEX
    Explanations

    references to third-party services and their relationships with other entities

    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
    acher
    -0.07
    ahun
    -0.07
    ợ
    -0.07
    zoom
    -0.06
     ?><?
    -0.06
    annes
    -0.06
     Mundo
    -0.06
    =YES
    -0.06
    emi
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
     independent
    0.07
     independently
    0.07
    ips
    0.06
     Pent
    0.06
    fq
    0.06
    Independ
    0.06
     Silver
    0.06
    unks
    0.06
     pent
    0.06
    IPS
    0.06
    Activations Density 0.002%

    No Known Activations