© 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. 124142
    Prev
    Next
    INDEX
    Explanations

    terms related to mining and the types of ore involved in the mining process

    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
    eon
    -0.07
    acs
    -0.07
    ender
    -0.06
    eos
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
    ky
    -0.06
    ext
    -0.06
    à¸ģ
    -0.06
     plain
    -0.06
    641
    -0.06
    POSITIVE LOGITS
    chestra
    0.09
     Dress
    0.08
    iginal
    0.07
    ìį¨
    0.07
    loff
    0.07
    dech
    0.07
    dec
    0.07
    ighth
    0.06
    ĵåIJį
    0.06
    BITS
    0.06
    Activations Density 0.004%

    No Known Activations