© 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. 9-LLAMASCOPE-RES-131K
    11. 97274
    Prev
    Next
    INDEX
    Explanations

    concepts related to randomized algorithms and their properties in graph theory

    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
    nock
    -0.07
    ëĬIJ
    -0.07
    èĥŀ
    -0.07
    ستاÙĨ
    -0.06
    anim
    -0.06
    AZY
    -0.06
    \views
    -0.06
     chim
    -0.06
     smo
    -0.06
    OutOfBoundsException
    -0.06
    POSITIVE LOGITS
    _MEDIUM
    0.06
     strategically
    0.06
     closely
    0.06
     Emerging
    0.06
     tightly
    0.06
    umba
    0.06
    pen
    0.06
    701
    0.06
    pv
    0.06
    alls
    0.05
    Activations Density 0.008%

    No Known Activations