Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43981
    Prev
    Next
    INDEX
    Explanations

    phrases involving invitations or commands that suggest taking action

    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
    acak
    -0.06
    ç«¥
    -0.05
    477
    -0.05
    è¥
    -0.05
    atre
    -0.05
    /System
    -0.05
    StackNavigator
    -0.05
     MessageType
    -0.05
    /the
    -0.05
    (the
    -0.05
    POSITIVE LOGITS
     TH
    0.10
     TB
    0.10
    TL
    0.10
    TP
    0.09
    TC
    0.09
     TW
    0.09
    TB
    0.09
    TW
    0.09
     TC
    0.09
    TPL
    0.09
    Activations Density 0.018%

    No Known Activations