© 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 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. 3507
    Prev
    Next
    INDEX
    Explanations

    instances of the word "posted."

    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
    à¸Ĭ
    -0.07
    çĵľ
    -0.07
    ledge
    -0.07
    serrat
    -0.06
    abo
    -0.06
    iamo
    -0.06
    ational
    -0.06
    jvu
    -0.06
    ÑĥÑĢн
    -0.06
    htags
    -0.06
    POSITIVE LOGITS
    anou
    0.07
    izo
    0.06
    OND
    0.06
    gow
    0.06
     productive
    0.06
    Degrees
    0.06
    Ħ
    0.06
     dilation
    0.06
    .orig
    0.06
    gew
    0.06
    Activations Density 0.002%

    No Known Activations