© 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. 41650
    Prev
    Next
    INDEX
    Explanations

    terms related to geological or environmental features

    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
     Giang
    -0.07
    isation
    -0.07
    ing
    -0.07
    erif
    -0.06
    вин
    -0.06
    nable
    -0.06
    ziej
    -0.06
    OAD
    -0.06
    oped
    -0.06
    ntity
    -0.06
    POSITIVE LOGITS
    ye
    0.07
    inis
    0.07
    sam
    0.06
    avers
    0.06
    ta
    0.06
    REFERRED
    0.06
    udev
    0.06
    acco
    0.06
    asco
    0.06
    116
    0.06
    Activations Density 0.001%

    No Known Activations