© 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. 62267
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to significant or extreme influence or impact

    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
    zan
    -0.10
    ialog
    -0.09
    clado
    -0.08
    iability
    -0.08
    bies
    -0.08
    ovel
    -0.08
    аÑĢÑħ
    -0.07
    sez
    -0.07
    ceptions
    -0.07
    ialized
    -0.07
    POSITIVE LOGITS
    ly
    0.10
    ingly
    0.09
     amounts
    0.08
     majority
    0.07
     support
    0.07
     amount
    0.07
     sands
    0.07
    dale
    0.07
    LY
    0.06
     evidence
    0.06
    Activations Density 0.004%

    No Known Activations