© 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. 895
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and comparisons

    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
    .scalablytyped
    -0.08
     physic
    -0.08
    ÅĻÃŃzenÃŃ
    -0.07
    íıIJ
    -0.07
    _MD
    -0.07
    íı
    -0.06
    166
    -0.06
    baugh
    -0.06
     sach
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
    adients
    0.07
    NOWLED
    0.06
    èĬ³
    0.06
    ronym
    0.06
    sis
    0.06
    isky
    0.06
    çıł
    0.05
    .Types
    0.05
    aroo
    0.05
    QUIRE
    0.05
    Activations Density 0.009%

    No Known Activations