© 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. 15-LLAMASCOPE-RES-131K
    11. 87766
    Prev
    Next
    INDEX
    Explanations

    references to specific nouns or pronouns related to objects and 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
    icut
    -0.09
    à¥įदर
    -0.07
    dm
    -0.07
     ga
    -0.07
    fos
    -0.07
    upal
    -0.07
    ©
    -0.07
    gang
    -0.07
    ãi
    -0.06
    cdn
    -0.06
    POSITIVE LOGITS
     PARTICULAR
    0.07
     CreateMap
    0.07
    oleon
    0.06
    /WebAPI
    0.06
    -yyyy
    0.06
    apper
    0.06
     MERCHANTABILITY
    0.06
     actionTypes
    0.06
    ANGLES
    0.06
     ÑģÑĤÑĢанÑĭ
    0.06
    Activations Density 0.009%

    No Known Activations