© 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. 79581
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "in" and specific punctuation

    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
    ãĥ©ãĥ³ãĥī
    -0.09
    NAL
    -0.09
    олом
    -0.09
    ãĢ
    -0.09
     Gaut
    -0.08
    etto
    -0.08
    ÑĩиÑģл
    -0.08
    èĮĤ
    -0.08
    å½Ĵ
    -0.08
    _transaksi
    -0.08
    POSITIVE LOGITS
     .
    0.06
    U
    0.06
    0
    0.06
    _
    0.06
     w
    0.06
    -
    0.06
    .
    0.06
     [
    0.06
     .↵
    0.06
    .↵
    0.05
    Activations Density 0.000%

    No Known Activations