© 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. 80890
    Prev
    Next
    INDEX
    Explanations

    references to locations or geopolitical contexts

    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
    RIPT
    -0.07
     parms
    -0.07
    IGHLIGHT
    -0.07
    REA
    -0.07
    ål
    -0.06
    ÅĻen
    -0.06
    ulum
    -0.06
    arakter
    -0.06
     srd
    -0.06
    ERRU
    -0.06
    POSITIVE LOGITS
    azers
    0.07
    ooks
    0.07
    ynet
    0.06
     anomal
    0.06
    Apart
    0.06
     Arts
    0.06
     lav
    0.06
    Ñĩин
    0.06
    ارش
    0.06
    azo
    0.06
    Activations Density 0.000%

    No Known Activations