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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3263
    Prev
    Next
    INDEX
    Explanations

    quotes and speech attribution in the text

    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
    ãĥĨãĥ«
    -0.08
    instein
    -0.08
     Gins
    -0.07
    ây
    -0.07
    hlas
    -0.07
    linger
    -0.07
    utex
    -0.07
    umont
    -0.07
    ondo
    -0.07
    rov
    -0.07
    POSITIVE LOGITS
     "
    0.08
     «
    0.08
     “
    0.08
    :
    0.07
    ain
    0.07
     ``
    0.06
     "(
    0.06
     '
    0.06
     simply
    0.06
    adel
    0.06
    Activations Density 0.020%

    No Known Activations