© 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. 95659
    Prev
    Next
    INDEX
    Explanations

    references to readers or audiences engaged with 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
    代
    -0.07
     character
    -0.07
    ech
    -0.06
     ÐĴи
    -0.06
    pts
    -0.06
    jspx
    -0.06
    conde
    -0.06
    arken
    -0.06
    akis
    -0.06
    644
    -0.06
    POSITIVE LOGITS
    hip
    0.09
    hood
    0.07
    er
    0.07
    /watch
    0.07
    347
    0.06
     dil
    0.06
    ono
    0.06
    onne
    0.06
     ÑģÑİ
    0.06
    ProcAddress
    0.06
    Activations Density 0.018%

    No Known Activations