© 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. 82447
    Prev
    Next
    INDEX
    Explanations

    details about settings and objects in a scene

    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
     pitch
    -0.06
     tender
    -0.06
    J
    -0.06
    U
    -0.06
     driv
    -0.06
    ardi
    -0.06
    ds
    -0.06
     retrospective
    -0.06
    Z
    -0.06
     stunt
    -0.06
    POSITIVE LOGITS
    oleÄį
    0.08
    âĹıâĹı
    0.08
    itorio
    0.08
    offsetof
    0.07
    ">//
    0.07
     bacheca
    0.07
    ием
    0.07
    ỳ
    0.07
     taxp
    0.07
    ikh
    0.07
    Activations Density 0.025%

    No Known Activations