© 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. 89059
    Prev
    Next
    INDEX
    Explanations

    references to original sources or content

    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
    åģ
    -0.07
     Elias
    -0.07
    ili
    -0.07
    etri
    -0.06
    endra
    -0.06
    .Singleton
    -0.06
     endpoints
    -0.06
    اÙĨÙĩ
    -0.06
    etak
    -0.06
    seealso
    -0.06
    POSITIVE LOGITS
    -original
    0.09
    /original
    0.08
    ches
    0.07
    åŃĺæ¡£
    0.07
     original
    0.07
    tors
    0.06
     оÑĢиг
    0.06
     originals
    0.06
    original
    0.06
    reno
    0.06
    Activations Density 0.000%

    No Known Activations