© 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. 93535
    Prev
    Next
    INDEX
    Explanations

    terms related to legal success and outcomes

    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
    kaar
    -0.06
    å¦ĥ
    -0.06
     âĹĦ
    -0.05
    543
    -0.05
    m
    -0.05
    dued
    -0.05
    ãģ£ãģ±
    -0.05
     Gron
    -0.05
    617
    -0.05
    uell
    -0.05
    POSITIVE LOGITS
     Clients
    0.09
    Clients
    0.09
     clients
    0.09
    clients
    0.08
    client
    0.08
     client
    0.08
     CLIENT
    0.07
     Client
    0.07
    Client
    0.07
    lients
    0.07
    Activations Density 0.003%

    No Known Activations