© 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. 9-LLAMASCOPE-RES-131K
    11. 97897
    Prev
    Next
    INDEX
    Explanations

    HTML document structure or specific document type definitions

    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
    ogn
    -0.06
    lege
    -0.06
    ola
    -0.06
    ulture
    -0.06
     lon
    -0.06
    -0.06
    alls
    -0.05
    andel
    -0.05
    olk
    -0.05
     mil
    -0.05
    POSITIVE LOGITS
    /Gate
    0.08
     اختÙĦ
    0.08
    галÑĸ
    0.07
    occo
    0.07
    ullan
    0.07
    EFA
    0.07
    YRO
    0.07
    eyse
    0.07
    /tinyos
    0.07
    ï¸
    0.07
    Activations Density 0.000%

    No Known Activations