© 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. 40313
    Prev
    Next
    INDEX
    Explanations

    terms related to modification or adjustment processes

    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
    ilos
    -0.07
    èĿ
    -0.07
    iales
    -0.07
    anim
    -0.06
    боÑĤ
    -0.06
    pos
    -0.06
    hest
    -0.06
    λα
    -0.06
    деÑĤ
    -0.06
     Speaker
    -0.06
    POSITIVE LOGITS
    reu
    0.07
    cÃŃ
    0.07
    -feed
    0.06
    ĵåIJį
    0.06
    KeyUp
    0.06
     ########.
    0.06
    oub
    0.06
    лон
    0.06
    OSH
    0.06
    ¾
    0.06
    Activations Density 0.002%

    No Known Activations