© 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. 119136
    Prev
    Next
    INDEX
    Explanations

    references to affordability in various contexts

    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
    Ìĥ
    -0.07
    eled
    -0.07
    üzel
    -0.07
    eler
    -0.07
    haled
    -0.07
    æķĪ
    -0.06
    tero
    -0.06
     fewer
    -0.06
    rom
    -0.06
    ical
    -0.06
    POSITIVE LOGITS
    ably
    0.11
    /free
    0.09
     lux
    0.07
    -priced
    0.07
    帯
    0.07
    sap
    0.07
    ços
    0.07
    isi
    0.07
    udge
    0.07
    .gc
    0.07
    Activations Density 0.006%

    No Known Activations