© 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. 15-LLAMASCOPE-RES-131K
    11. 88223
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential, use, and context in discussions

    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
    plist
    -0.06
    ochond
    -0.06
     Cush
    -0.06
     mor
    -0.06
    peria
    -0.06
     another
    -0.05
    otal
    -0.05
    postalcode
    -0.05
    ruc
    -0.05
    plit
    -0.05
    POSITIVE LOGITS
    vens
    0.08
    828
    0.08
    ãĤ¸
    0.08
    zimmer
    0.07
    ãĥ«ãĥķ
    0.07
    _Selection
    0.07
    ktop
    0.07
    éf
    0.07
    εβ
    0.07
    ajar
    0.07
    Activations Density 0.021%

    No Known Activations