© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75195
    Prev
    Next
    INDEX
    Explanations

    LaTeX codes and formatting specifications for figures and graphs in scientific documentation

    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
     Hardy
    -0.06
    ilder
    -0.06
     written
    -0.05
    ollen
    -0.05
     melted
    -0.05
    inar
    -0.05
    ови
    -0.05
    owie
    -0.05
     fasc
    -0.05
    out
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ÃĵN
    0.08
     Kurum
    0.08
    Edition
    0.08
     ense
    0.07
    EMON
    0.07
     Dash
    0.07
    å®ı
    0.07
    #ad
    0.07
    Advertisements
    0.07
    Activations Density 0.017%

    No Known Activations