© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    instances of the word "different" and its variations

    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
    arken
    -0.07
    ê¹
    -0.07
    üçük
    -0.07
    oric
    -0.07
    ouble
    -0.07
    own
    -0.07
    inee
    -0.06
    ubu
    -0.06
    ãĤ¦ãĥ³
    -0.06
    ivor
    -0.06
    POSITIVE LOGITS
    iating
    0.22
    iator
    0.17
    ially
    0.15
    iates
    0.15
    iable
    0.15
    iators
    0.14
    iability
    0.14
    iations
    0.13
    ials
    0.12
    iation
    0.11
    Activations Density 0.060%

    No Known Activations