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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84421
    Prev
    Next
    INDEX
    Explanations

    information related to the sizes and measurements of ships and mines

    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
    ofile
    -0.06
     kole
    -0.06
    MG
    -0.06
     fashion
    -0.06
    èĪ¬
    -0.06
     BG
    -0.06
     Genius
    -0.06
     startPos
    -0.06
    980
    -0.05
    631
    -0.05
    POSITIVE LOGITS
     measured
    0.08
    measurement
    0.07
    istra
    0.07
    aleigh
    0.07
     briefly
    0.07
    ilis
    0.07
     finished
    0.07
     measurement
    0.07
     currently
    0.06
     measuring
    0.06
    Activations Density 0.007%

    No Known Activations