© 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. 9-LLAMASCOPE-RES-131K
    11. 95648
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions in complex sentences

    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
    .scalablytyped
    -0.07
    orca
    -0.07
    _nama
    -0.07
    gt
    -0.07
     ÑĤака
    -0.06
    aci
    -0.06
     piè
    -0.06
    uez
    -0.06
    lush
    -0.06
    poÄįet
    -0.06
    POSITIVE LOGITS
    cp
    0.07
    éŀ
    0.06
    conde
    0.06
    icional
    0.06
    Reviewer
    0.06
     innoc
    0.06
     Citizenship
    0.06
    RunWith
    0.05
    iners
    0.05
    BarController
    0.05
    Activations Density 0.027%

    No Known Activations