© 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 EvalsExportsAPI 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. 77301
    Prev
    Next
    INDEX
    Explanations

    references to bridges and bodies of water

    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
    387
    -0.06
     climbers
    -0.06
    ocz
    -0.06
    -initialized
    -0.06
     facil
    -0.06
    eil
    -0.06
    _EPS
    -0.06
     staircase
    -0.06
     locksmith
    -0.06
    ायल
    -0.06
    POSITIVE LOGITS
     gap
    0.09
     across
    0.09
    Across
    0.08
     Across
    0.08
    gap
    0.08
     distance
    0.07
    _between
    0.07
    _GAP
    0.07
     between
    0.07
     span
    0.07
    Activations Density 0.012%

    No Known Activations