© 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. 69397
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements and relevant factors affecting future outcomes

    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
    abis
    -0.07
    cznie
    -0.07
    posables
    -0.06
    ãĥ³ãĤº
    -0.06
    .tf
    -0.06
    央
    -0.06
    oco
    -0.06
    tü
    -0.06
    awner
    -0.06
    olet
    -0.06
    POSITIVE LOGITS
     future
    0.07
     forward
    0.07
    icing
    0.06
     Gee
    0.06
    NU
    0.06
    StackNavigator
    0.06
    future
    0.06
    Forward
    0.06
    itch
    0.06
     Forward
    0.06
    Activations Density 0.001%

    No Known Activations