© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84843
    Prev
    Next
    INDEX
    Explanations

    instances of the word "real" related to various contexts in the document

    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
    se
    -0.07
    ese
    -0.07
    sip
    -0.07
    ed
    -0.06
    idor
    -0.06
    onian
    -0.06
     inse
    -0.06
    ÑģÑĤÑĢи
    -0.06
    rav
    -0.06
    prov
    -0.06
    POSITIVE LOGITS
    /false
    0.09
    atively
    0.09
    ilk
    0.08
    -ÑĤаки
    0.07
    yen
    0.07
    uxt
    0.07
    abar
    0.07
    uzz
    0.06
    -league
    0.06
    uddy
    0.06
    Activations Density 0.009%

    No Known Activations