© 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. 22-LLAMASCOPE-RES-131K
    11. 4302
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration and partnerships

    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
    chter
    -0.08
    anton
    -0.07
    ament
    -0.07
     ç§
    -0.07
    aturday
    -0.07
    angan
    -0.07
    recio
    -0.07
     ~>
    -0.06
    gos
    -0.06
    Modificar
    -0.06
    POSITIVE LOGITS
     such
    0.18
    such
    0.15
     Such
    0.13
     SUCH
    0.13
     another
    0.12
    è¿Ļä¹Ī
    0.12
    Such
    0.12
    å¦ĤæѤ
    0.12
     à¤ĩतन
    0.11
    another
    0.11
    Activations Density 0.031%

    No Known Activations