© 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. 83920
    Prev
    Next
    INDEX
    Explanations

    semantic structure or markup related to configuration or settings in a programming context

    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
    ãĢģæľ¬
    -0.08
    berger
    -0.07
     Rew
    -0.07
    ynchronously
    -0.07
     holding
    -0.06
    ypi
    -0.06
     Holding
    -0.06
    odont
    -0.06
    .ma
    -0.06
    .ic
    -0.06
    POSITIVE LOGITS
    åľŃ
    0.06
    ote
    0.06
     _:
    0.06
    OTE
    0.06
    ign
    0.06
    ovit
    0.06
    uly
    0.06
    doi
    0.06
    ãĥ©
    0.06
    roof
    0.06
    Activations Density 0.010%

    No Known Activations