Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5332
    Prev
    Next
    INDEX
    Explanations

    various metadata elements, particularly dates and titles related to events or 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
     Pare
    -0.06
    åĭĩ
    -0.06
    کارÛĮ
    -0.06
    urette
    -0.06
    mons
    -0.06
    okable
    -0.06
    enticator
    -0.05
    link
    -0.05
    .AutoComplete
    -0.05
    ÑĢаÑħ
    -0.05
    POSITIVE LOGITS
     May
    0.08
    leftright
    0.08
     July
    0.07
    -fontawesome
    0.07
    Sphere
    0.07
    ASI
    0.07
    .scalablytyped
    0.07
    atem
    0.07
    ERRU
    0.07
     onDataChange
    0.07
    Activations Density 0.030%

    No Known Activations