© 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. 73277
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to dates

    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
    achte
    -0.07
    artial
    -0.06
    à¹ģล
    -0.06
     Meyer
    -0.06
    ipt
    -0.06
    à¸Ńลล
    -0.05
    ÙĦÙĬÙĦ
    -0.05
    ätze
    -0.05
    ÄĽk
    -0.05
     unders
    -0.05
    POSITIVE LOGITS
    aram
    0.07
    ARAM
    0.07
    edeki
    0.07
    quila
    0.07
    irse
    0.07
    .Serve
    0.07
    ylko
    0.07
     Wor
    0.06
    WebResponse
    0.06
    ikler
    0.06
    Activations Density 0.010%

    No Known Activations