© 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. 40537
    Prev
    Next
    INDEX
    Explanations

    comments in code

    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
    bert
    -0.07
    andas
    -0.07
    ropol
    -0.07
    vio
    -0.06
    à¸Ħ
    -0.06
    andal
    -0.06
    ivial
    -0.06
    _HARD
    -0.06
    (video
    -0.06
    @js
    -0.06
    POSITIVE LOGITS
    eki
    0.08
    infeld
    0.07
    ding
    0.07
    icc
    0.06
    ghi
    0.06
    ungan
    0.06
    ouve
    0.06
    \CMS
    0.06
    aaS
    0.06
    ãĥķãĤ
    0.06
    Activations Density 0.007%

    No Known Activations