© 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. 59124
    Prev
    Next
    INDEX
    Explanations

    terms related to universal access or availability

    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
    ochen
    -0.07
    çī¹æ®Ĭ
    -0.06
    MI
    -0.06
     Featured
    -0.06
     Amir
    -0.06
    amen
    -0.05
    upy
    -0.05
    TestCategory
    -0.05
    wayne
    -0.05
    arry
    -0.05
    POSITIVE LOGITS
     every
    0.08
    every
    0.08
    ensus
    0.07
    æ¯ı
    0.07
     VÅ¡
    0.07
    ifetime
    0.07
     Every
    0.07
    elpers
    0.07
     EVERY
    0.07
     member
    0.06
    Activations Density 0.021%

    No Known Activations