© 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. 130528
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to normalization and scaling

    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
    oq
    -0.07
    reak
    -0.07
    .TestCase
    -0.07
    ltk
    -0.06
     Boy
    -0.06
    oque
    -0.06
    azzi
    -0.06
    pest
    -0.06
    _equ
    -0.06
     nues
    -0.06
    POSITIVE LOGITS
     factor
    0.14
     factors
    0.13
    factor
    0.12
    -factor
    0.11
    Factor
    0.10
    .factor
    0.10
     Factors
    0.10
     fakt
    0.10
    _factor
    0.10
    _FACTOR
    0.10
    Activations Density 0.274%

    No Known Activations