© 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. 120715
    Prev
    Next
    INDEX
    Explanations

    HTML and PHP syntax elements within the text

    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
    oog
    -0.06
    út
    -0.06
    ãģĹãģĭ
    -0.06
    olding
    -0.06
    .rpm
    -0.06
    öm
    -0.06
     tess
    -0.06
    ads
    -0.06
    188
    -0.05
    sand
    -0.05
    POSITIVE LOGITS
    oreach
    0.07
    eh
    0.07
    ½æķ°
    0.07
    structor
    0.07
    abis
    0.07
    ophon
    0.06
     Ñģпад
    0.06
    aleigh
    0.06
    efe
    0.06
    lias
    0.06
    Activations Density 0.014%

    No Known Activations