© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71153
    Prev
    Next
    INDEX
    Explanations

    financial transactions and agreements

    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
    leta
    -0.07
     Circus
    -0.07
    SSIP
    -0.07
    387
    -0.06
     crem
    -0.06
     Chop
    -0.06
     Preview
    -0.06
    (PC
    -0.06
    alat
    -0.06
    posit
    -0.06
    POSITIVE LOGITS
     agreed
    0.08
     cash
    0.08
     ÙĨÙĤد
    0.07
     Kaynak
    0.07
    _WM
    0.07
    agos
    0.07
     agreeing
    0.07
    agus
    0.06
    cash
    0.06
    erval
    0.06
    Activations Density 0.005%

    No Known Activations