© 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. 117036
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a comparison or assessment of similarities

    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
    uell
    -0.07
    AndGet
    -0.07
    STANCE
    -0.07
     meanwhile
    -0.06
    andest
    -0.06
    ieux
    -0.06
    onium
    -0.06
    .Names
    -0.06
    byname
    -0.06
    ãģĹãģĭãģĹ
    -0.06
    POSITIVE LOGITS
     consequently
    0.07
    reas
    0.07
     even
    0.07
     accompanying
    0.06
    ris
    0.06
     Antony
    0.06
     Weiner
    0.06
    اسÙĩ
    0.06
     dokonce
    0.06
    WIN
    0.06
    Activations Density 0.131%

    No Known Activations