© 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. 58632
    Prev
    Next
    INDEX
    Explanations

    sequential or directional phrases related to paths or roads

    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
    chants
    -0.06
    cit
    -0.06
    burg
    -0.06
     Cous
    -0.06
     Dart
    -0.05
    áy
    -0.05
     Kemp
    -0.05
     transplant
    -0.05
     precaution
    -0.05
     fut
    -0.05
    POSITIVE LOGITS
    _next
    0.07
     next
    0.07
    ovenant
    0.07
    next
    0.07
    .next
    0.07
    -next
    0.07
     Continuing
    0.07
    ç¶ļ
    0.07
    kou
    0.07
    emark
    0.07
    Activations Density 0.018%

    No Known Activations