© 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. 78082
    Prev
    Next
    INDEX
    Explanations

    references to educational resources and literature

    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
     computer
    -0.06
    tte
    -0.06
    Inputs
    -0.06
    éŁ
    -0.06
    adata
    -0.06
    ätt
    -0.05
    ows
    -0.05
     Newspaper
    -0.05
    UBL
    -0.05
     Beaut
    -0.05
    POSITIVE LOGITS
    سط
    0.08
    ackage
    0.07
     STM
    0.07
    ãĤµãĤ¤
    0.07
    ibi
    0.07
    ihu
    0.07
    pron
    0.07
    iž
    0.07
     Partial
    0.07
     Pron
    0.07
    Activations Density 0.008%

    No Known Activations