© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128472
    Prev
    Next
    INDEX
    Explanations

    references to software models and their configurations

    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
    ion
    -0.07
     Airways
    -0.06
    uspend
    -0.06
    npos
    -0.06
    anya
    -0.06
    .tencent
    -0.06
    jon
    -0.06
    odelist
    -0.06
    enthal
    -0.06
    EEDED
    -0.06
    POSITIVE LOGITS
    UME
    0.07
    404
    0.06
    vÃŃc
    0.06
     SPDX
    0.06
    TypeDef
    0.06
    еÑĢе
    0.06
    otine
    0.06
    PHPUnit
    0.06
    .sig
    0.06
    баÑĩ
    0.06
    Activations Density 0.002%

    No Known Activations