© 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. 120758
    Prev
    Next
    INDEX
    Explanations

    special characters or accented letters in text

    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
    argent
    -0.08
    phant
    -0.08
    ional
    -0.07
    olut
    -0.07
    ursal
    -0.07
    irts
    -0.06
    mand
    -0.06
    films
    -0.06
    iae
    -0.06
    villa
    -0.06
    POSITIVE LOGITS
    ULO
    0.07
    Ñĸно
    0.06
     Bite
    0.06
    å¹¹
    0.06
    ạt
    0.06
     win
    0.06
    nett
    0.06
    ÏĥÏĦÏĮ
    0.06
    blr
    0.06
    ãĤ¢ãĥ³
    0.06
    Activations Density 0.002%

    No Known Activations