© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75414
    Prev
    Next
    INDEX
    Explanations

    programming functions and methods related to Docker and environment variable manipulation

    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
     bacheca
    -0.08
     ``(
    -0.08
    crement
    -0.08
    BCM
    -0.08
    ÑİÑĢ
    -0.08
    俺ãģ¯
    -0.07
    HRESULT
    -0.07
    cq
    -0.07
    ενο
    -0.07
    人æ°Ĺ
    -0.07
    POSITIVE LOGITS
     "
    0.07
     '
    0.06
     (
    0.06
     this
    0.06
    ere
    0.05
     of
    0.05
     my
    0.05
    Question
    0.05
    uck
    0.05
     {
    0.05
    Activations Density 0.015%

    No Known Activations