© 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. 22-LLAMASCOPE-RES-131K
    11. 4060
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific disciplines, particularly in medicine, mathematics, and natural sciences

    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
    iliary
    -0.08
    .Foundation
    -0.07
    åľ°ä¸ĭ
    -0.07
    ipse
    -0.07
    805
    -0.06
    illes
    -0.06
    .assertThat
    -0.06
    éĤ¦
    -0.06
    lius
    -0.06
    ÏĦζ
    -0.06
    POSITIVE LOGITS
    âĸº
    0.06
    >null
    0.06
    anvas
    0.06
    _esc
    0.06
    .marker
    0.06
    ::-
    0.06
    677
    0.06
     \|
    0.06
     âĢº
    0.06
    orida
    0.06
    Activations Density 0.002%

    No Known Activations