© 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. 78093
    Prev
    Next
    INDEX
    Explanations

    historical references and origins related to animals and places

    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
    amage
    -0.07
    ERO
    -0.07
    oba
    -0.07
    chten
    -0.07
    antity
    -0.07
    jeme
    -0.07
    å¡
    -0.07
    orque
    -0.07
    izmet
    -0.07
    duc
    -0.07
    POSITIVE LOGITS
     spread
    0.08
    aram
    0.07
     immigration
    0.07
     dispers
    0.07
     migrations
    0.07
     acc
    0.07
     movement
    0.06
    Spread
    0.06
     movements
    0.06
     routes
    0.06
    Activations Density 0.009%

    No Known Activations