© 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. 127674
    Prev
    Next
    INDEX
    Explanations

    analytical verbs related to exploration and evaluation

    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
     Hamp
    -0.07
    caff
    -0.07
    ucha
    -0.06
    auf
    -0.06
     itself
    -0.06
    630
    -0.06
    екÑĥ
    -0.06
     ÙĦذا
    -0.06
    fan
    -0.06
     wel
    -0.06
    POSITIVE LOGITS
     how
    0.12
    how
    0.10
    ona
    0.07
    OMB
    0.07
     ways
    0.07
    utt
    0.07
     recent
    0.07
     briefly
    0.07
     some
    0.07
     why
    0.07
    Activations Density 0.036%

    No Known Activations