© 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. 119198
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to returning or extracting entities or objects

    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
    uzzi
    -0.07
     plat
    -0.07
     ä¸
    -0.06
    łģ
    -0.06
    depth
    -0.06
    offset
    -0.06
     res
    -0.06
    _Release
    -0.06
    ince
    -0.06
    ilk
    -0.06
    POSITIVE LOGITS
     intact
    0.09
    YRO
    0.07
     minus
    0.07
    usercontent
    0.07
    ä¾Ľ
    0.06
     completed
    0.06
     beaten
    0.06
    ãĥijãĥ³
    0.06
    entes
    0.06
    fromJson
    0.06
    Activations Density 0.060%

    No Known Activations