© 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. 9-LLAMASCOPE-RES-131K
    11. 97634
    Prev
    Next
    INDEX
    Explanations

    references and discussions about proactive measures and initiatives

    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
    ÑĮ
    -0.08
    edback
    -0.08
    ãĥĵãĥ¼
    -0.07
     Parkway
    -0.07
    occo
    -0.07
    imei
    -0.07
    itsu
    -0.07
    akes
    -0.07
    urve
    -0.07
    vÄĽ
    -0.06
    POSITIVE LOGITS
    (Action
    0.06
    -action
    0.06
    /action
    0.06
     distribution
    0.05
    èµ·æĿ¥
    0.05
    /rem
    0.05
    -results
    0.05
     action
    0.05
    KN
    0.05
     Rand
    0.05
    Activations Density 0.013%

    No Known Activations