© 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. 69351
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting markers indicating transitions or separations in text

    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
    agens
    -0.08
    ozor
    -0.07
    opp
    -0.07
    .gwt
    -0.07
    esus
    -0.07
    opa
    -0.07
    opus
    -0.07
    indow
    -0.07
    orney
    -0.07
    æĬ±
    -0.07
    POSITIVE LOGITS
    HEME
    0.06
     ER
    0.06
    allon
    0.06
    0.05
     “
    0.05
     PH
    0.05
     Rin
    0.05
     ${({
    0.05
     DIY
    0.05
     Potter
    0.05
    Activations Density 0.001%

    No Known Activations