© 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. 54233
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other linking words that connect phrases or clauses

    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
    ingu
    -0.06
    alta
    -0.05
    urent
    -0.05
    ynam
    -0.05
    ynos
    -0.05
    ypress
    -0.05
    ymoon
    -0.05
    vars
    -0.05
    herent
    -0.05
    ernal
    -0.05
    POSITIVE LOGITS
     other
    0.27
    other
    0.22
    åħ¶ä»ĸ
    0.22
    -other
    0.21
     OTHER
    0.20
     autres
    0.19
    Other
    0.19
     åħ¶ä»ĸ
    0.19
     Other
    0.19
     andere
    0.19
    Activations Density 0.031%

    No Known Activations