© 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. 778
    Prev
    Next
    INDEX
    Explanations

    suggestions for building and maintaining friendships

    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
    odel
    -0.06
    rana
    -0.06
    sty
    -0.06
    [
    -0.06
     ↵
    -0.06
     surviv
    -0.05
    stu
    -0.05
    æ£
    -0.05
    uhe
    -0.05
     Accord
    -0.05
    POSITIVE LOGITS
     Networking
    0.08
    ernet
    0.07
    NETWORK
    0.07
    *)((
    0.07
     Lonely
    0.07
    954
    0.07
    ãĥ³ãĥĸ
    0.07
    åºľ
    0.07
    ConnectionFactory
    0.07
    _parallel
    0.07
    Activations Density 0.008%

    No Known Activations