© 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. 108609
    Prev
    Next
    INDEX
    Explanations

    strong sentiments or emphatic statements

    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
     recipro
    -0.06
    abox
    -0.06
    irror
    -0.06
    xfb
    -0.06
    rese
    -0.06
    erken
    -0.06
    essa
    -0.06
     bet
    -0.06
    ickest
    -0.06
    esan
    -0.05
    POSITIVE LOGITS
    obia
    0.06
     Schro
    0.06
     Grinder
    0.06
    rido
    0.06
    isma
    0.06
    fec
    0.06
    imar
    0.06
     gran
    0.06
    ожеÑĤ
    0.06
     currentItem
    0.06
    Activations Density 0.000%

    No Known Activations