© 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. 41545
    Prev
    Next
    INDEX
    Explanations

    terms related to participation and investment from various parties in a project or situation

    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
    è¾ij
    -0.08
    ick
    -0.08
    RLF
    -0.07
    Å©
    -0.07
    iams
    -0.07
    nels
    -0.07
    ERGE
    -0.07
    endi
    -0.07
    anders
    -0.07
    ãĥ«ãĥķ
    -0.07
    POSITIVE LOGITS
    holder
    0.12
    holders
    0.10
    pole
    0.08
    isha
    0.07
    house
    0.07
    cipher
    0.07
    pile
    0.07
    knife
    0.07
    overflow
    0.07
    craft
    0.06
    Activations Density 0.005%

    No Known Activations