© 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. 39220
    Prev
    Next
    INDEX
    Explanations

    mentions of programming languages and technology-related terms

    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
    lessly
    -0.07
    çģ
    -0.07
    ablish
    -0.06
    ále
    -0.06
    ZO
    -0.06
    /filepath
    -0.06
    radient
    -0.06
    eyse
    -0.06
    ovit
    -0.06
    огод
    -0.06
    POSITIVE LOGITS
    екÑĥ
    0.07
    mie
    0.06
     >=
    0.06
     parl
    0.06
    >=
    0.06
     Reese
    0.06
    zk
    0.06
    áºŃu
    0.06
    urger
    0.06
    ogan
    0.06
    Activations Density 0.019%

    No Known Activations