© 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. 123756
    Prev
    Next
    INDEX
    Explanations

    references to remote user connectivity and technology

    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
    ema
    -0.07
    emas
    -0.07
    osa
    -0.06
    éri
    -0.06
    evin
    -0.06
    aminer
    -0.06
    è³ŀ
    -0.06
     Surveillance
    -0.06
    ulum
    -0.06
    :"-"`↵
    -0.06
    POSITIVE LOGITS
    격
    0.07
     Schro
    0.07
     access
    0.07
    vice
    0.06
    Cit
    0.06
     productivity
    0.06
     rem
    0.06
     productive
    0.06
     Tommy
    0.06
    Cad
    0.06
    Activations Density 0.019%

    No Known Activations