© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29194
    Prev
    Next
    INDEX
    Explanations

    formal mathematical theorems and lemmas

    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
    åŃĺäºİ
    -0.06
    et
    -0.06
     Company
    -0.06
    ieux
    -0.06
     Voor
    -0.06
    asar
    -0.06
     Archives
    -0.06
    abled
    -0.06
     Net
    -0.05
    onomic
    -0.05
    POSITIVE LOGITS
    ÅĻes
    0.08
    COR
    0.08
    ¯u
    0.07
    /Area
    0.07
    ÙĦÙĦ
    0.07
    ANE
    0.07
     Král
    0.07
    stime
    0.07
    .TextAlignment
    0.07
    /Instruction
    0.07
    Activations Density 0.045%

    No Known Activations