© 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. 61129
    Prev
    Next
    INDEX
    Explanations

    programming and coding structures, particularly related to setting titles, action results, and theme options in web development

    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
    assen
    -0.07
    ŀĭ
    -0.07
    >Show
    -0.06
    -manager
    -0.06
    irit
    -0.06
    uyá»ģn
    -0.06
     Sheridan
    -0.06
    216
    -0.06
    PublicKey
    -0.06
    ateral
    -0.06
    POSITIVE LOGITS
     title
    0.17
    title
    0.15
     Title
    0.14
     TITLE
    0.14
    .title
    0.14
    :title
    0.14
    -title
    0.13
    =title
    0.13
     titles
    0.13
    (title
    0.13
    Activations Density 0.008%

    No Known Activations