© 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. 72844
    Prev
    Next
    INDEX
    Explanations

    discussions about the impact of technology on business and communication

    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
    ãn
    -0.07
    име
    -0.07
    ìĿį
    -0.07
     defaultMessage
    -0.06
    unken
    -0.06
     ><?
    -0.06
     bÄĻdÄħ
    -0.06
     bul
    -0.06
    ôt
    -0.06
    ialect
    -0.06
    POSITIVE LOGITS
     virtual
    0.07
    usi
    0.07
     advent
    0.07
     revolution
    0.06
    kud
    0.06
    iqueta
    0.06
    virtual
    0.06
     entirely
    0.06
     modern
    0.06
     invention
    0.06
    Activations Density 0.011%

    No Known Activations