© 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. 108350
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss pros and cons or advantages and disadvantages

    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
    leur
    -0.07
    ele
    -0.07
    象
    -0.07
     nouve
    -0.06
    ptive
    -0.06
    enance
    -0.06
    eval
    -0.06
    ¤íĶĦ
    -0.06
    horse
    -0.06
    eq
    -0.06
    POSITIVE LOGITS
    ieri
    0.07
    riet
    0.07
    olas
    0.06
    кол
    0.06
    /WebAPI
    0.06
     refunded
    0.06
     âĨĵ
    0.06
    DOT
    0.06
    ocz
    0.06
     âĨij
    0.06
    Activations Density 0.000%

    No Known Activations