© 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. 62987
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements

    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
    pedo
    -0.07
     Ded
    -0.06
    ivar
    -0.06
    ãĥ¼ãĥ©
    -0.06
    zas
    -0.06
    ertest
    -0.06
    .twitch
    -0.06
    addock
    -0.06
    èĮĥ
    -0.06
    ott
    -0.05
    POSITIVE LOGITS
    ogn
    0.07
    ETCH
    0.07
    ãĥ³ãĥ
    0.07
    enus
    0.07
    _NOP
    0.07
    大åħ¨
    0.07
     Hag
    0.07
    aterno
    0.06
    ahat
    0.06
    Technical
    0.06
    Activations Density 0.006%

    No Known Activations