© 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. 76226
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of engines

    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
    aul
    -0.07
     Sheldon
    -0.06
     anon
    -0.06
     recharge
    -0.06
    icken
    -0.06
    odable
    -0.06
    çıį
    -0.06
    rica
    -0.06
    KHTML
    -0.06
    POSITIVE LOGITS
     engine
    0.09
     fuel
    0.08
     oil
    0.08
     engines
    0.07
     power
    0.07
    Pitch
    0.07
     pitch
    0.07
    (power
    0.07
     Engine
    0.07
     Pitch
    0.07
    Activations Density 0.007%

    No Known Activations