© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 38858
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    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
    269
    -0.06
     Mits
    -0.06
    lla
    -0.06
    uat
    -0.06
    sol
    -0.06
    ayan
    -0.06
    wiÄħ
    -0.06
    AMP
    -0.05
    ep
    -0.05
    ısından
    -0.05
    POSITIVE LOGITS
     say
    0.10
    åIJ§
    0.09
     term
    0.09
     perhaps
    0.09
     ÑģказаÑĤÑĮ
    0.08
    argo
    0.08
     noun
    0.08
     sagen
    0.08
     rather
    0.08
     decir
    0.08
    Activations Density 0.084%

    No Known Activations