© 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. 5-LLAMASCOPE-RES-131K
    11. 125580
    Prev
    Next
    INDEX
    Explanations

    references to specific events or occurrences

    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
    ahu
    -0.06
     PureComponent
    -0.06
    .'<
    -0.06
     Wand
    -0.06
    apan
    -0.06
     Pu
    -0.06
     pu
    -0.06
     karak
    -0.06
    ilibrium
    -0.06
    hips
    -0.06
    POSITIVE LOGITS
    aland
    0.07
    ssi
    0.07
     cre
    0.06
    оÑĥ
    0.06
    oi
    0.06
    487
    0.06
    sez
    0.06
     mong
    0.06
    -level
    0.06
    ãĤ¹ãĥĨãĤ£
    0.06
    Activations Density 0.007%

    No Known Activations