© 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. 105898
    Prev
    Next
    INDEX
    Explanations

    instances of time and events

    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
    meld
    -0.07
    óng
    -0.06
    ough
    -0.06
    atto
    -0.06
    ield
    -0.06
    BR
    -0.06
    ervers
    -0.06
    currentColor
    -0.06
    enge
    -0.06
     Mist
    -0.06
    POSITIVE LOGITS
    èĪŀ
    0.07
    jing
    0.07
    fuse
    0.06
    affen
    0.06
    476
    0.06
    .recycle
    0.06
    naire
    0.06
     Stephan
    0.06
    AutoSize
    0.06
    adesh
    0.06
    Activations Density 0.000%

    No Known Activations