© 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. 93285
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or parameters in relation to studies or technical specifications

    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
    ozor
    -0.06
    uhn
    -0.06
    IBC
    -0.06
     McGregor
    -0.06
     ih
    -0.06
    icter
    -0.06
     Cecil
    -0.06
    .Helper
    -0.06
    .resource
    -0.06
    eparator
    -0.06
    POSITIVE LOGITS
    icle
    0.07
    ertas
    0.07
    erta
    0.06
    MBED
    0.06
    uts
    0.06
    ocrates
    0.06
    \<^
    0.06
    ãĥ¼ãĥ
    0.06
    strup
    0.06
    acin
    0.06
    Activations Density 0.235%

    No Known Activations