© 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. 40726
    Prev
    Next
    INDEX
    Explanations

    references to credits and recognition 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
    AI
    -0.07
    ترÛĮ
    -0.07
    ergarten
    -0.06
    ish
    -0.06
    ież
    -0.06
    /small
    -0.06
    alytics
    -0.06
    istry
    -0.06
    erman
    -0.06
    RIORITY
    -0.06
    POSITIVE LOGITS
    ting
    0.09
    worthy
    0.09
    ably
    0.09
    ted
    0.08
    zman
    0.08
    noop
    0.08
     Kris
    0.07
    fully
    0.07
    imb
    0.07
    ts
    0.07
    Activations Density 0.009%

    No Known Activations