© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107332
    Prev
    Next
    INDEX
    Explanations

    references to copyright and ownership

    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
    illi
    -0.07
    igli
    -0.07
    479
    -0.07
    acic
    -0.07
    etti
    -0.07
    hua
    -0.06
    416
    -0.06
    illas
    -0.06
    iddi
    -0.06
    ÙħاÙħ
    -0.06
    POSITIVE LOGITS
    Îŀ
    0.07
    rof
    0.07
    곤
    0.07
    à¤Ĥर
    0.06
    rl
    0.06
    è§ī
    0.06
    isans
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    ENDOR
    0.06
     Hollow
    0.06
    Activations Density 0.001%

    No Known Activations