© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125481
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics or metrics

    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
     DÄĽ
    -0.08
    ̣
    -0.08
    iš
    -0.08
     имÑĥ
    -0.08
    мага
    -0.08
     ÄĮer
    -0.08
    üç
    -0.08
    iare
    -0.07
    wake
    -0.07
    dum
    -0.07
    POSITIVE LOGITS
    oplayer
    0.06
    ady
    0.06
    ï¸ı
    0.06
    tring
    0.06
     Harmony
    0.05
     Vog
    0.05
    âĢį
    0.05
    arsing
    0.05
    ertos
    0.05
    APS
    0.05
    Activations Density 0.045%

    No Known Activations