© 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. 40298
    Prev
    Next
    INDEX
    Explanations

    references to software projects and their handling processes

    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
    ishly
    -0.08
    ï
    -0.07
    اÙĨÙĩ
    -0.07
    sic
    -0.07
     dm
    -0.06
    odge
    -0.06
    cout
    -0.06
    anlık
    -0.06
    705
    -0.06
    haft
    -0.06
    POSITIVE LOGITS
    iner
    0.19
    chy
    0.14
    /her
    0.14
    /th
    0.13
    zelf
    0.12
    unes
    0.12
    /us
    0.12
    inerary
    0.11
    self
    0.10
    SELF
    0.10
    Activations Density 0.130%

    No Known Activations