© 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. 107762
    Prev
    Next
    INDEX
    Explanations

    terms associated with informative content

    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
    ocol
    -0.08
    /left
    -0.07
    esel
    -0.07
    rez
    -0.07
    åij½
    -0.06
    mai
    -0.06
    orum
    -0.06
    itar
    -0.06
    ê¶Į
    -0.06
    arily
    -0.06
    POSITIVE LOGITS
    -packed
    0.07
    ative
    0.07
    ctor
    0.07
    bst
    0.07
    ctors
    0.06
    enance
    0.06
    -information
    0.06
    覧
    0.06
    -rich
    0.06
    /use
    0.06
    Activations Density 0.011%

    No Known Activations