© 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. 16817
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight a specific emphasis or focus on particular topics

    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
    olik
    -0.08
    ron
    -0.07
    è´
    -0.07
    zin
    -0.07
    sville
    -0.07
    anza
    -0.07
    ÑĨвеÑĤ
    -0.07
    imen
    -0.06
    zim
    -0.06
    chip
    -0.06
    POSITIVE LOGITS
     ones
    0.07
     towards
    0.07
    INDOW
    0.07
     toward
    0.06
    ëĬIJ
    0.06
     those
    0.06
    ìĪľ
    0.06
     ELF
    0.06
    IED
    0.06
    оÑĤÑĭ
    0.06
    Activations Density 0.004%

    No Known Activations