© 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. 84823
    Prev
    Next
    INDEX
    Explanations

    instructions related to downloading or saving images and files

    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
    Æ°Æ¡ng
    -0.07
    icked
    -0.06
    NaN
    -0.06
    anuts
    -0.06
    essler
    -0.06
    ves
    -0.06
    stdClass
    -0.06
     ved
    -0.06
    essaging
    -0.06
    Saint
    -0.06
    POSITIVE LOGITS
     CONSEQUENTIAL
    0.07
    139
    0.07
    arrera
    0.07
     mouse
    0.06
    otas
    0.06
     lược
    0.06
    iese
    0.06
    کر
    0.06
    HS
    0.06
     mur
    0.06
    Activations Density 0.001%

    No Known Activations