© 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. 119010
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and permissions management

    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
     Gel
    -0.07
    ennon
    -0.07
    ourcem
    -0.07
    egment
    -0.06
    okie
    -0.06
     Guth
    -0.06
    Ionic
    -0.06
     gel
    -0.06
    urgeon
    -0.06
     γε
    -0.06
    POSITIVE LOGITS
    .transfer
    0.07
    warz
    0.07
     Daw
    0.07
     DPS
    0.07
    ORITY
    0.07
     rust
    0.06
     Bashar
    0.06
     sill
    0.06
    olly
    0.06
     Raz
    0.06
    Activations Density 0.001%

    No Known Activations