© 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. 15-LLAMASCOPE-RES-131K
    11. 88115
    Prev
    Next
    INDEX
    Explanations

    references to CDs and music albums

    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
    -0.07
    t
    -0.06
    /sources
    -0.06
    est
    -0.06
    y
    -0.06
    fa
    -0.06
    in
    -0.06
    141
    -0.06
    333
    -0.05
    444
    -0.05
    POSITIVE LOGITS
    aday
    0.09
    iasi
    0.09
    -ROM
    0.09
    ãĤ
    0.09
    /mp
    0.08
    zilla
    0.08
    anced
    0.08
    Ìĥ
    0.08
    AGMA
    0.08
    icari
    0.08
    Activations Density 0.009%

    No Known Activations