© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84834
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and interaction

    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
    leg
    -0.07
     res
    -0.06
     **
    -0.06
     t
    -0.05
     without
    -0.05
    legt
    -0.05
     copies
    -0.05
    Ø°
    -0.05
    h
    -0.05
     fore
    -0.05
    POSITIVE LOGITS
     Äijá»ĥ
    0.12
     Ñīоб
    0.12
     ÑĩÑĤобÑĭ
    0.12
     aby
    0.11
     afin
    0.09
     inorder
    0.09
     to
    0.08
    æīįèĥ½
    0.08
    (#)
    0.08
     ÄIJá»ĥ
    0.08
    Activations Density 0.002%

    No Known Activations