© 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. 120858
    Prev
    Next
    INDEX
    Explanations

    mentions of initiation or establishment of processes

    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
    ptune
    -0.08
    erli
    -0.08
    pearance
    -0.08
    ollapsed
    -0.08
    ories
    -0.08
    lesc
    -0.07
    ÃŃc
    -0.07
    acades
    -0.07
    adera
    -0.07
    aklı
    -0.07
    POSITIVE LOGITS
    åĢij
    0.08
    们
    0.08
    /student
    0.08
    /custom
    0.07
     who
    0.07
     whom
    0.07
     عزÛĮز
    0.06
    ëħ
    0.06
     chatter
    0.05
    -operator
    0.05
    Activations Density 0.049%

    No Known Activations