© 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. 15-LLAMASCOPE-RES-131K
    11. 86896
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks and references to sources or literature

    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
     cis
    -0.06
    Bookmark
    -0.05
    ois
    -0.05
    ÙĦÙĬÙĩ
    -0.05
     undefined
    -0.05
     x
    -0.05
     r
    -0.05
     rem
    -0.05
    oint
    -0.05
    à¥įह
    -0.05
    POSITIVE LOGITS
     VÅ¡ech
    0.08
    gia
    0.08
    ginas
    0.07
    dden
    0.07
    APON
    0.07
    UILTIN
    0.07
    ÃŃÅĻ
    0.07
    gens
    0.07
     kvin
    0.07
    è¡£
    0.07
    Activations Density 0.001%

    No Known Activations