© 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 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. 128825
    Prev
    Next
    INDEX
    Explanations

    references to testing or assertions in code

    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
    .mixin
    -0.06
    loi
    -0.06
     bust
    -0.06
     Gregory
    -0.06
    urre
    -0.06
    جة
    -0.06
     ret
    -0.06
    rott
    -0.05
    adesh
    -0.05
     Virtual
    -0.05
    POSITIVE LOGITS
    оÑıÑĤ
    0.08
    ÑĥлÑİ
    0.08
    slaught
    0.08
    ovit
    0.07
    @nate
    0.07
     withString
    0.07
    dbe
    0.07
    vyk
    0.07
    gross
    0.07
    isman
    0.07
    Activations Density 0.004%

    No Known Activations