© 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. 15-LLAMASCOPE-RES-131K
    11. 90280
    Prev
    Next
    INDEX
    Explanations

    questions related to Greek theatre and drama

    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
    CEL
    -0.08
    ingt
    -0.07
    nosis
    -0.07
    SES
    -0.07
    lett
    -0.07
    assel
    -0.07
    aw
    -0.06
    ijk
    -0.06
    ấp
    -0.06
     Stranger
    -0.06
    POSITIVE LOGITS
    ovÃŃ
    0.06
    GitHub
    0.06
    aci
    0.06
    ansa
    0.06
     Morr
    0.06
    /WebAPI
    0.06
     etc
    0.06
     INF
    0.06
    rowsable
    0.06
    ì¿
    0.06
    Activations Density 0.001%

    No Known Activations