© 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. 61644
    Prev
    Next
    INDEX
    Explanations

    references to scientific literature and publication details

    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
    phis
    -0.07
    OrFail
    -0.06
    usch
    -0.06
    emez
    -0.06
    inger
    -0.06
    ær
    -0.06
     chi
    -0.06
    ادا
    -0.06
    endent
    -0.06
    acha
    -0.06
    POSITIVE LOGITS
    ORIA
    0.07
    oria
    0.07
    179
    0.06
     Keller
    0.06
    183
    0.06
     Bab
    0.06
    queda
    0.06
    ntity
    0.06
    eam
    0.06
    tm
    0.06
    Activations Density 0.011%

    No Known Activations