© 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. 14734
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms

    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
    ober
    -0.06
    enek
    -0.06
    FO
    -0.06
     Abed
    -0.06
    ---@
    -0.06
     wikipedia
    -0.06
     jal
    -0.06
    accent
    -0.06
    inky
    -0.05
    kov
    -0.05
    POSITIVE LOGITS
     formerly
    0.07
    /Instruction
    0.07
    atore
    0.07
    MOVED
    0.06
     Ñįлек
    0.06
     now
    0.06
     Former
    0.06
    ayıp
    0.06
    implify
    0.06
    woke
    0.06
    Activations Density 0.001%

    No Known Activations