© 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. 126377
    Prev
    Next
    INDEX
    Explanations

    references to starting different types of small businesses and services

    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
    laus
    -0.08
    á»iji
    -0.07
    MF
    -0.07
    RAFT
    -0.07
    stad
    -0.07
    icon
    -0.07
    ourcem
    -0.07
    à¤¾à¤Ł
    -0.07
     Econ
    -0.07
     Commercial
    -0.06
    POSITIVE LOGITS
     service
    0.08
     services
    0.08
    -service
    0.07
    service
    0.07
     XYZ
    0.07
     Services
    0.07
    /service
    0.06
    /services
    0.06
     serviço
    0.06
     tutor
    0.06
    Activations Density 0.033%

    No Known Activations