© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74827
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tags related to navigation and dropdown menus

    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
     suk
    -0.07
    yles
    -0.07
     kvinne
    -0.07
    avenport
    -0.07
    oklyn
    -0.07
    ÑģÑĤи
    -0.07
    okol
    -0.07
    eko
    -0.07
    олож
    -0.06
     stra
    -0.06
    POSITIVE LOGITS
    otta
    0.07
    exas
    0.07
    _iff
    0.06
     Conrad
    0.06
    #Region
    0.06
    åķĬåķĬ
    0.06
     offsetof
    0.06
     Zero
    0.06
    .scalablytyped
    0.06
    awah
    0.06
    Activations Density 0.001%

    No Known Activations