© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107305
    Prev
    Next
    INDEX
    Explanations

    details about audio production equipment and facilities

    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
    emoc
    -0.06
     spas
    -0.06
    _hz
    -0.06
     once
    -0.06
    leta
    -0.06
     dear
    -0.06
    jee
    -0.06
     Sou
    -0.05
     when
    -0.05
    wand
    -0.05
    POSITIVE LOGITS
     capability
    0.10
     capable
    0.09
     capabilities
    0.09
    capability
    0.08
    èĥ½åĬĽ
    0.08
    Forgery
    0.07
    orz
    0.07
    éħį
    0.07
     comfortably
    0.07
     capacity
    0.07
    Activations Density 0.022%

    No Known Activations