© 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. 73398
    Prev
    Next
    INDEX
    Explanations

    terms related to specific activities or roles in sports or technical contexts

    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
    ekli
    -0.06
    871
    -0.06
    ÑģÑĮко
    -0.06
    ?url
    -0.06
    (æľ¨
    -0.06
    phylum
    -0.06
    244
    -0.06
    ÃĸL
    -0.06
    horn
    -0.06
    _PRE
    -0.06
    POSITIVE LOGITS
    IFEST
    0.07
    ifest
    0.07
    ãģ»ãģĨ
    0.07
    CAC
    0.07
    ãĥĥãĥĪ
    0.06
    762
    0.06
     nÃło
    0.06
    STS
    0.06
    ascar
    0.06
    DITION
    0.06
    Activations Density 0.026%

    No Known Activations