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

    Neuronpedia

    APICircuit 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. 5551
    Prev
    Next
    INDEX
    Explanations

    references to a specific location, particularly Mt. Kailash

    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
    mith
    -0.07
    ÑĢаÑģÑĤ
    -0.07
    acus
    -0.07
    essian
    -0.07
    chl
    -0.06
     ÏĥÏĦι
    -0.06
    ãĤ¹ãĤ¯
    -0.06
    eldom
    -0.06
    569
    -0.06
     domination
    -0.06
    POSITIVE LOGITS
    uku
    0.08
    leur
    0.08
     Affero
    0.08
    ties
    0.08
    ings
    0.08
    ors
    0.08
    unce
    0.07
    ored
    0.07
    ly
    0.07
    lette
    0.07
    Activations Density 0.008%

    No Known Activations