© 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. 118691
    Prev
    Next
    INDEX
    Explanations

    discussions about grammatical structure or word usage

    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
     harbor
    -0.06
    à¹īà¸Ńà¸Ļ
    -0.06
    imator
    -0.06
    ç´ł
    -0.06
    510
    -0.06
    hazi
    -0.06
    929
    -0.06
    zo
    -0.06
    ÈĻi
    -0.06
    iano
    -0.06
    POSITIVE LOGITS
    APTER
    0.07
    æ¸Ī
    0.07
    ãĤŃãĥ³ãĤ°
    0.07
    igraph
    0.07
    angstrom
    0.07
    omp
    0.07
     plur
    0.07
     Klopp
    0.06
    .ObjectId
    0.06
     Hindered
    0.06
    Activations Density 0.063%

    No Known Activations