Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56085
    Prev
    Next
    INDEX
    Explanations

    references to sections and methodologies in academic papers

    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
     Pik
    -0.07
    encies
    -0.07
    ä¹ħ
    -0.06
    éľ²
    -0.06
    Ìģ
    -0.06
    nu
    -0.06
    ite
    -0.06
    é¢ĺ
    -0.06
    ower
    -0.06
    ulp
    -0.06
    POSITIVE LOGITS
     section
    0.32
     Section
    0.27
    section
    0.27
     sections
    0.27
    -section
    0.25
    Section
    0.25
     SECTION
    0.24
    _section
    0.23
     subsection
    0.23
    .section
    0.23
    Activations Density 0.158%

    No Known Activations