© 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. 94142
    Prev
    Next
    INDEX
    Explanations

    occurrences of announcements and events, particularly regarding new launches or updates

    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
    eldorf
    -0.06
    å¢
    -0.06
    ousse
    -0.06
    orrent
    -0.06
    çģ
    -0.06
    ìłIJ
    -0.05
    åħ´
    -0.05
    roph
    -0.05
    abor
    -0.05
    üp
    -0.05
    POSITIVE LOGITS
    ONGL
    0.08
    imest
    0.08
     -----------------------------------------------------------------------------↵
    0.07
     gib
    0.07
    alles
    0.06
     kostenlose
    0.06
    alist
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    iid
    0.06
    áºŃt
    0.06
    Activations Density 0.037%

    No Known Activations