© 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 EvalsExportsAPI 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. 59311
    Prev
    Next
    INDEX
    Explanations

    words related to unresolved issues or matters awaiting attention

    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
     fil
    -0.07
    usto
    -0.06
     connexion
    -0.06
    iske
    -0.06
    ÄĻ
    -0.06
    jian
    -0.06
    allo
    -0.06
     bias
    -0.06
    orde
    -0.06
     wet
    -0.05
    POSITIVE LOGITS
    .foundation
    0.07
    oton
    0.07
    estro
    0.06
     Glo
    0.06
     recep
    0.06
    @brief
    0.06
    ÑĦиÑĨи
    0.06
    Æ¡m
    0.06
     rhet
    0.06
    ilateral
    0.06
    Activations Density 0.000%

    No Known Activations