© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61795
    Prev
    Next
    INDEX
    Explanations

    phrases related to business partnerships and collaborations

    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
    iez
    -0.09
    onte
    -0.09
    jian
    -0.08
    erse
    -0.07
    üny
    -0.07
    ênh
    -0.07
    поÑģеÑĢед
    -0.07
     adulte
    -0.07
    IPP
    -0.06
    leting
    -0.06
    POSITIVE LOGITS
    ÙĪØ·
    0.07
    çĿ
    0.06
    .LookAndFeel
    0.06
     Morrow
    0.06
     assassin
    0.06
     Balls
    0.06
     various
    0.06
     Woodward
    0.05
    undler
    0.05
     partner
    0.05
    Activations Density 0.008%

    No Known Activations