© 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. 129135
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" used in various contexts to connect ideas

    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
    athed
    -0.06
    ï¸ı
    -0.06
    plement
    -0.06
     head
    -0.06
     lah
    -0.05
    ORT
    -0.05
     situation
    -0.05
    yas
    -0.05
    essages
    -0.05
    -head
    -0.05
    POSITIVE LOGITS
    rie
    0.08
    odon
    0.08
    rex
    0.08
    rieb
    0.07
    raf
    0.07
    viz
    0.07
    kees
    0.07
    vanced
    0.07
    sei
    0.07
    roph
    0.07
    Activations Density 0.037%

    No Known Activations