© 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. 94503
    Prev
    Next
    INDEX
    Explanations

    quotation marks and references to reviews

    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
    annonce
    -0.08
    ãĥ©ãĤ¤ãĥĪ
    -0.07
    æµľ
    -0.07
    zyst
    -0.06
    PTS
    -0.06
    @update
    -0.06
     karÄ±ÅŁ
    -0.06
    aÄĩ
    -0.06
     Dys
    -0.06
    à¹īà¸Ńย
    -0.06
    POSITIVE LOGITS
    amik
    0.07
     whose
    0.06
     which
    0.06
     Irma
    0.06
     hi
    0.06
     Sz
    0.06
     impe
    0.06
     Hi
    0.06
     @}
    0.05
     plastic
    0.05
    Activations Density 0.014%

    No Known Activations