© 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 EvalsExportsAPI 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. 85671
    Prev
    Next
    INDEX
    Explanations

    terms related to biological taxonomy and classification

    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
    assis
    -0.07
     kaç
    -0.06
    fsp
    -0.06
    ienes
    -0.06
    aison
    -0.06
    hone
    -0.06
     Sloan
    -0.06
    UGC
    -0.06
    asca
    -0.06
    aland
    -0.06
    POSITIVE LOGITS
    uct
    0.07
    INFRINGEMENT
    0.06
    elly
    0.06
    -inline
    0.06
    770
    0.06
    avigator
    0.06
     Loud
    0.06
    ensen
    0.06
    iple
    0.06
    inherits
    0.06
    Activations Density 0.005%

    No Known Activations