© 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. 17-LLAMASCOPE-RES-131K
    11. 29782
    Prev
    Next
    INDEX
    Explanations

    terms related to inheritance and legacy

    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
    enia
    -0.07
    ew
    -0.07
    aram
    -0.07
    alo
    -0.06
    aque
    -0.06
    yz
    -0.06
    terior
    -0.06
    yon
    -0.06
    .pan
    -0.06
    sembly
    -0.06
    POSITIVE LOGITS
     apparent
    0.06
    èĢħçļĦ
    0.06
    tees
    0.06
    ence
    0.06
    iband
    0.06
    ÛĮÙĩ
    0.06
    ãĥ¼ãĥķ
    0.06
    Pk
    0.06
    igor
    0.06
    722
    0.06
    Activations Density 0.007%

    No Known Activations