© 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. 17-LLAMASCOPE-RES-131K
    11. 42379
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate continuation or emphasis

    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
    ़
    -0.07
    462
    -0.07
    -0.06
    anco
    -0.06
     scr
    -0.06
    onga
    -0.06
    iesel
    -0.06
    279
    -0.06
    ombo
    -0.06
    ona
    -0.06
    POSITIVE LOGITS
    urr
    0.07
    ãĤ¦ãĥ³
    0.07
    ufen
    0.07
    rens
    0.07
    acon
    0.07
    eri
    0.06
     oneself
    0.06
    μÏĢ
    0.06
    jev
    0.06
     Watt
    0.06
    Activations Density 0.000%

    No Known Activations