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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92073
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize a strong preference or importance

    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
    chio
    -0.07
    ocy
    -0.07
    aptive
    -0.07
    å¹
    -0.06
    ucci
    -0.06
    Overrides
    -0.06
     vou
    -0.06
     Deck
    -0.06
    ivated
    -0.06
    úng
    -0.06
    POSITIVE LOGITS
     other
    0.15
     others
    0.15
     else
    0.14
    others
    0.13
     autres
    0.12
    åħ¶ä»ĸ
    0.12
     otros
    0.12
    other
    0.11
     otras
    0.11
    else
    0.10
    Activations Density 0.005%

    No Known Activations