© 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. 15-LLAMASCOPE-RES-131K
    11. 90154
    Prev
    Next
    INDEX
    Explanations

    nouns associated with entities or categories that may indicate significant events or actions

    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
    ãĤ¸ãĤ¢
    -0.08
    baum
    -0.07
    heim
    -0.07
    iaux
    -0.07
    ollapsed
    -0.07
    ichel
    -0.07
    oxel
    -0.07
    iben
    -0.07
    VT
    -0.07
    unik
    -0.06
    POSITIVE LOGITS
     several
    0.07
     two
    0.06
     unspecified
    0.06
     three
    0.06
     Nos
    0.06
     Several
    0.06
     algun
    0.06
     اÙĦØ«
    0.06
     some
    0.05
     various
    0.05
    Activations Density 0.039%

    No Known Activations