© 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. 17-LLAMASCOPE-RES-131K
    11. 61335
    Prev
    Next
    INDEX
    Explanations

    concepts related to technology and engineering principles

    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
    ukt
    -0.07
    fid
    -0.06
     Eve
    -0.06
    νÏĦ
    -0.05
     أر
    -0.05
    ãĤĵãģ¨
    -0.05
     Quad
    -0.05
    ellite
    -0.05
    KEN
    -0.05
     Dex
    -0.05
    POSITIVE LOGITS
     principle
    0.17
     Principle
    0.16
     principles
    0.14
     principals
    0.13
     Principles
    0.12
     пÑĢинÑĨип
    0.11
     principio
    0.10
     princ
    0.10
     Princip
    0.10
    inciple
    0.09
    Activations Density 0.027%

    No Known Activations