© 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. 4108
    Prev
    Next
    INDEX
    Explanations

    terms that indicate coexistence or cooperation

    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
    eyn
    -0.09
    å«Į
    -0.08
    .synthetic
    -0.08
    ãĥ³ãĥĶ
    -0.07
    _ARGS
    -0.07
    /commons
    -0.07
    acin
    -0.07
    isia
    -0.06
    èĦ±
    -0.06
    âĶIJ
    -0.06
    POSITIVE LOGITS
     co
    0.09
     com
    0.09
     concurrent
    0.08
     existing
    0.08
     occurring
    0.08
     simultaneous
    0.07
     Concurrent
    0.07
     simultaneously
    0.07
     con
    0.07
    existing
    0.07
    Activations Density 0.006%

    No Known Activations