© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    references to group activities or accommodations

    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
    avigate
    -0.08
     Sink
    -0.07
    oxel
    -0.07
    pras
    -0.07
    ughs
    -0.06
    imli
    -0.06
    imson
    -0.06
    rios
    -0.06
    sink
    -0.06
    .cloudflare
    -0.06
    POSITIVE LOGITS
     groups
    0.15
     Groups
    0.13
    groups
    0.12
     group
    0.12
    Groups
    0.12
     GROUP
    0.11
     corporate
    0.10
     Corporate
    0.10
    group
    0.10
     grup
    0.10
    Activations Density 0.047%

    No Known Activations