© 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. 69735
    Prev
    Next
    INDEX
    Explanations

    phrases that describe transformations or transitions between states or entities

    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
    ç·
    -0.07
    inalg
    -0.07
    IAS
    -0.07
    ias
    -0.07
    ENCHMARK
    -0.06
    yat
    -0.06
    iat
    -0.06
    iw
    -0.06
    éĢı
    -0.06
    zp
    -0.06
    POSITIVE LOGITS
     something
    0.09
     become
    0.08
     a
    0.08
     addCriterion
    0.08
     becomes
    0.07
     full
    0.07
     an
    0.07
    serter
    0.07
    something
    0.06
     Actual
    0.06
    Activations Density 0.020%

    No Known Activations