© 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. 15570
    Prev
    Next
    INDEX
    Explanations

    references to animal tracks and signs of wildlife presence

    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
    олом
    -0.07
    898
    -0.07
    eree
    -0.07
    923
    -0.06
    boro
    -0.06
    rawer
    -0.06
    alach
    -0.06
    938
    -0.06
     Prompt
    -0.06
    illaume
    -0.06
    POSITIVE LOGITS
     foot
    0.10
     tread
    0.10
     footprint
    0.09
     trail
    0.09
     footsteps
    0.09
     Foot
    0.08
    -foot
    0.08
    è¸
    0.08
     Shoes
    0.08
    breadcrumbs
    0.08
    Activations Density 0.005%

    No Known Activations