© 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. 107532
    Prev
    Next
    INDEX
    Explanations

    references to comparison and related terms

    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
    ereotype
    -0.08
    .nz
    -0.08
    ery
    -0.08
    ration
    -0.07
    ated
    -0.07
    çĦ¶
    -0.07
    ensburg
    -0.07
    OTH
    -0.07
    ough
    -0.07
    enson
    -0.07
    POSITIVE LOGITS
    atively
    0.07
    favor
    0.07
     unfavor
    0.07
     to
    0.07
     favor
    0.07
    èĤ©
    0.07
    isons
    0.07
    encing
    0.07
    oder
    0.06
    ãģ¹
    0.06
    Activations Density 0.023%

    No Known Activations