© 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. 118604
    Prev
    Next
    INDEX
    Explanations

    repetitions of the phrase "of the."

    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
    ãģ°ãģĭãĤĬ
    -0.08
    رÙĪز
    -0.07
    TEMPL
    -0.07
    ardon
    -0.06
    .microsoft
    -0.06
    ÑĢин
    -0.06
    رز
    -0.06
    .rf
    -0.06
    krom
    -0.06
     knocking
    -0.06
    POSITIVE LOGITS
    arra
    0.07
     someone
    0.07
    .shtml
    0.06
     INLINE
    0.06
    uls
    0.06
    éĢ
    0.06
     statue
    0.06
     Dean
    0.06
    INET
    0.06
    lic
    0.06
    Activations Density 0.028%

    No Known Activations