© 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. 9-LLAMASCOPE-RES-131K
    11. 97220
    Prev
    Next
    INDEX
    Explanations

    references to online publications or sources

    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
    atches
    -0.06
     Meadows
    -0.06
    raz
    -0.06
    aspers
    -0.06
    ennon
    -0.06
     Canter
    -0.06
    aran
    -0.06
     Ale
    -0.06
    enson
    -0.06
    hus
    -0.06
    POSITIVE LOGITS
    amba
    0.07
    ê³Ħ
    0.07
    orgt
    0.06
    æĺĩ
    0.06
    idend
    0.06
    ovky
    0.06
     nth
    0.06
    adors
    0.06
    iset
    0.06
    adius
    0.06
    Activations Density 0.001%

    No Known Activations