© 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. 41557
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and equations related to statistical models and integration

    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
     plá
    -0.07
    elden
    -0.06
    .cleanup
    -0.06
    afil
    -0.06
    atoi
    -0.06
    plural
    -0.06
    EZ
    -0.06
    èle
    -0.06
    _lb
    -0.06
     Credentials
    -0.06
    POSITIVE LOGITS
     equal
    0.12
     equality
    0.12
     exactly
    0.11
    equal
    0.10
     Equal
    0.10
     neutrality
    0.09
     Exactly
    0.09
    Equal
    0.09
     precisely
    0.08
     Neutral
    0.08
    Activations Density 0.177%

    No Known Activations