© 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. 124342
    Prev
    Next
    INDEX
    Explanations

    references to the weight and specifications of vehicles

    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
    Ïį
    -0.06
     wid
    -0.06
     Processing
    -0.06
     cÃŃ
    -0.06
    band
    -0.06
    bread
    -0.06
    ade
    -0.06
    wide
    -0.06
     ÑĪиÑĢ
    -0.06
     ste
    -0.06
    POSITIVE LOGITS
     weight
    0.18
     weights
    0.16
     Weight
    0.15
    weight
    0.15
    Weight
    0.14
     WEIGHT
    0.14
    -weight
    0.14
     weigh
    0.13
    Weights
    0.13
    .weight
    0.13
    Activations Density 0.025%

    No Known Activations