© 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. 9-LLAMASCOPE-RES-131K
    11. 96684
    Prev
    Next
    INDEX
    Explanations

    references to operating systems and software versions

    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
    ytt
    -0.08
    iona
    -0.08
    oje
    -0.07
    cus
    -0.07
    byt
    -0.07
    ISTER
    -0.07
    Multi
    -0.06
    à¸ĺ
    -0.06
     sÃŃ
    -0.06
    има
    -0.06
    POSITIVE LOGITS
    witch
    0.06
    ableObject
    0.06
     Gene
    0.05
    ÄĻk
    0.05
    ãĤĬãģ«
    0.05
    achu
    0.05
    trag
    0.05
    ature
    0.05
    acht
    0.05
    hai
    0.05
    Activations Density 0.002%

    No Known Activations