© 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. 73537
    Prev
    Next
    INDEX
    Explanations

    positive sentiments expressed towards authors and their works

    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
     itself
    -0.08
    reen
    -0.07
    Å¡t
    -0.06
     ours
    -0.06
     competitive
    -0.06
    icie
    -0.06
     parties
    -0.06
    ensor
    -0.06
    vented
    -0.06
     ch
    -0.05
    POSITIVE LOGITS
    yat
    0.10
    agas
    0.08
    aller
    0.08
     můj
    0.07
    abcdefghijkl
    0.07
    rahim
    0.07
    ENCHMARK
    0.07
    æĨ
    0.07
    念
    0.07
    alam
    0.07
    Activations Density 0.053%

    No Known Activations