© 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. 30822
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in."

    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
    a
    -0.07
    inn
    -0.06
    jure
    -0.06
    e
    -0.06
     Morav
    -0.06
    thon
    -0.06
     prot
    -0.06
     numel
    -0.06
     Abd
    -0.06
    оза
    -0.06
    POSITIVE LOGITS
    atform
    0.09
    stantiate
    0.07
    ีà¸Ńย
    0.07
    terior
    0.07
    èµĦ
    0.07
    uç
    0.07
    uo
    0.07
    andon
    0.06
    GetSize
    0.06
    adays
    0.06
    Activations Density 0.005%

    No Known Activations