© 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. 105234
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly nested objects or arrays

    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
    atos
    -0.06
    ato
    -0.06
    аÑĤо
    -0.06
    .setResult
    -0.06
    rong
    -0.06
    ots
    -0.06
    getResult
    -0.05
    ÎĪ
    -0.05
    Äįin
    -0.05
    ERA
    -0.05
    POSITIVE LOGITS
    ailed
    0.08
    orado
    0.07
    ccak
    0.07
    amik
    0.07
    ksam
    0.07
     thiên
    0.07
    onis
    0.06
    isay
    0.06
    iced
    0.06
    inders
    0.06
    Activations Density 0.010%

    No Known Activations