© 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. 15-LLAMASCOPE-RES-131K
    11. 62445
    Prev
    Next
    INDEX
    Explanations

    sentences discussing sports performance and expectations

    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
    éľ
    -0.07
    ãĥ³ãĥij
    -0.07
    oir
    -0.07
     guardar
    -0.07
    ù
    -0.07
    urai
    -0.07
    Ãły
    -0.06
     swal
    -0.06
     guarda
    -0.06
    struments
    -0.06
    POSITIVE LOGITS
     hopefully
    0.08
     maybe
    0.07
     will
    0.06
     Hopefully
    0.06
     if
    0.06
     potentially
    0.06
    atan
    0.06
     likely
    0.06
     possibly
    0.06
     slightest
    0.06
    Activations Density 0.039%

    No Known Activations