© 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. 76838
    Prev
    Next
    INDEX
    Explanations

    phrases related to setup or preparation for events or situations

    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
    uzzi
    -0.06
     Progress
    -0.06
     strictly
    -0.06
    ixon
    -0.06
    iki
    -0.06
    ulia
    -0.06
    cea
    -0.05
     bump
    -0.05
    á»
    -0.05
     specified
    -0.05
    POSITIVE LOGITS
    610
    0.08
    embro
    0.07
    TEGER
    0.07
     for
    0.07
    gel
    0.07
    ninger
    0.07
    recio
    0.06
    orpion
    0.06
    .ali
    0.06
    otland
    0.06
    Activations Density 0.008%

    No Known Activations