© 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. 15-LLAMASCOPE-RES-131K
    11. 61820
    Prev
    Next
    INDEX
    Explanations

    references to statistical or mathematical concepts and expressions

    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
    Ø®ÙĪاÙĨ
    -0.07
     physic
    -0.07
    eki
    -0.07
     operand
    -0.07
    IENT
    -0.07
    деÑĢ
    -0.07
    eydi
    -0.06
    üven
    -0.06
     lục
    -0.06
    (bc
    -0.06
    POSITIVE LOGITS
    inux
    0.06
    åı
    0.06
     Travis
    0.06
     manifest
    0.06
    otch
    0.06
    QP
    0.06
     SM
    0.05
     ho
    0.05
     so
    0.05
    robat
    0.05
    Activations Density 0.011%

    No Known Activations