© 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. 78286
    Prev
    Next
    INDEX
    Explanations

    terms related to community solidarity and support for collective action

    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
     Pip
    -0.06
    à¸ĵะ
    -0.06
     ClassName
    -0.06
    abant
    -0.06
     seh
    -0.06
     thus
    -0.06
    iche
    -0.06
    наÑĩала
    -0.06
     maka
    -0.06
    igan
    -0.06
    POSITIVE LOGITS
     ones
    0.13
     other
    0.13
    other
    0.11
     equally
    0.10
    åħ¶ä»ĸ
    0.10
    ãģĿãģ®ä»ĸ
    0.10
     ÑĸнÑĪиÑħ
    0.09
     others
    0.09
     Ones
    0.09
     дÑĢÑĥгими
    0.08
    Activations Density 0.048%

    No Known Activations