© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94400
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and"

    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
    [sizeof
    -0.06
    igm
    -0.06
    541
    -0.06
    kw
    -0.06
     manic
    -0.06
     Roose
    -0.06
     FIR
    -0.06
    rende
    -0.06
     Rousse
    -0.06
    KW
    -0.06
    POSITIVE LOGITS
    érie
    0.08
     bundle
    0.07
     Bund
    0.07
    utes
    0.07
     Bundle
    0.07
    importe
    0.07
    Ñĵ
    0.06
    ecz
    0.06
    dden
    0.06
    ãĥ³ãĤº
    0.06
    Activations Density 0.000%

    No Known Activations