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

    Neuronpedia

    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. 89616
    Prev
    Next
    INDEX
    Explanations

    details about the condition and history of a classic car

    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
    lean
    -0.06
    /per
    -0.06
    ouri
    -0.06
     Independ
    -0.06
    oured
    -0.06
     Coff
    -0.05
    ben
    -0.05
    la
    -0.05
    a
    -0.05
     ul
    -0.05
    POSITIVE LOGITS
     original
    0.10
    -original
    0.08
    original
    0.08
    krom
    0.08
     gá»ijc
    0.08
     intact
    0.08
    /original
    0.08
     ORIGINAL
    0.07
    (original
    0.07
    avad
    0.07
    Activations Density 0.009%

    No Known Activations