© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53911
    Prev
    Next
    INDEX
    Explanations

    inquiries about conditions or situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    hape
    -0.07
    ãĥ¼ãĥ©
    -0.06
    ahir
    -0.06
     accordingly
    -0.06
    rone
    -0.06
    кав
    -0.06
    .hr
    -0.06
    BoxLayout
    -0.06
    antro
    -0.06
    BUFFER
    -0.06
    POSITIVE LOGITS
     OnTrigger
    0.06
    yx
    0.06
    703
    0.06
    csi
    0.06
    %C
    0.06
    bers
    0.06
    istar
    0.06
     Khi
    0.06
     Vintage
    0.06
    .getOwnProperty
    0.06
    Activations Density 0.029%

    No Known Activations