© 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. 17-LLAMASCOPE-RES-131K
    11. 85681
    Prev
    Next
    INDEX
    Explanations

    HTML and XML closing tags

    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
    ing
    -0.08
    åĵģ
    -0.07
    ãĥ¬ãĥ¼
    -0.07
    anch
    -0.06
    ING
    -0.06
    urr
    -0.06
    enh
    -0.06
    ConfigurationException
    -0.06
    orks
    -0.06
    //↵↵
    -0.06
    POSITIVE LOGITS
    ftware
    0.08
    agara
    0.08
    ellaneous
    0.08
    fra
    0.07
    sgi
    0.07
    ollo
    0.07
    ividual
    0.07
    ouis
    0.07
    oulos
    0.07
    hei
    0.07
    Activations Density 0.009%

    No Known Activations