© 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. 16305
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts that indicate availability or entry to resources 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
    ilig
    -0.08
    éIJĺ
    -0.07
    ENS
    -0.07
    jev
    -0.07
    eller
    -0.07
    оÑģÑĤав
    -0.07
    ÑĮко
    -0.07
     chung
    -0.07
    _SUPPORTED
    -0.07
    fern
    -0.06
    POSITIVE LOGITS
    ibilities
    0.07
     to
    0.07
     via
    0.07
    abile
    0.07
    åĪ°çļĦ
    0.07
    ability
    0.06
    ibly
    0.06
    ibe
    0.06
    ants
    0.06
    able
    0.06
    Activations Density 0.010%

    No Known Activations