© 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. 55282
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and scientific concepts

    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
    лин
    -0.07
    -ing
    -0.07
    ACL
    -0.06
    iac
    -0.06
    áce
    -0.06
    ://
    -0.06
     frei
    -0.06
    istor
    -0.06
    .opend
    -0.06
    å»·
    -0.06
    POSITIVE LOGITS
    raquo
    0.07
    nicos
    0.07
     division
    0.06
    oris
    0.06
     -
    0.06
    :
    0.06
     commission
    0.06
    ा:
    0.06
     section
    0.06
    erece
    0.06
    Activations Density 0.113%

    No Known Activations