© 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. 9-LLAMASCOPE-RES-131K
    11. 95699
    Prev
    Next
    INDEX
    Explanations

    references to entrance exam-related content

    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
    etto
    -0.06
     Misc
    -0.06
    ulu
    -0.06
    екÑĥ
    -0.06
     Tam
    -0.06
     Luft
    -0.06
    astery
    -0.06
    IFI
    -0.06
    pend
    -0.06
    !=(
    -0.06
    POSITIVE LOGITS
    ayan
    0.07
    INES
    0.06
    751
    0.06
    angu
    0.06
    声ãĤĴ
    0.06
    áŀ¶áŀ
    0.06
    UTE
    0.06
    ÑĮÑİÑĤ
    0.06
    uite
    0.06
     ört
    0.06
    Activations Density 0.010%

    No Known Activations