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. 31-LLAMASCOPE-RES-131K
    6. 44104
    Prev
    Next
    INDEX
    Explanations

    encoded or special characters in the text

    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
    ullets
    -0.07
     spar
    -0.06
    SPAN
    -0.06
    drv
    -0.06
    eler
    -0.06
     доÑģ
    -0.06
    ableView
    -0.06
    all
    -0.06
    aepernick
    -0.06
    aller
    -0.06
    POSITIVE LOGITS
     Icon
    0.06
    ensity
    0.06
    orman
    0.06
     Administrator
    0.06
    Parcelable
    0.06
    ãĥ³ãĤ¬
    0.05
     tune
    0.05
    icut
    0.05
     icon
    0.05
     Tribune
    0.05
    Activations Density 0.002%

    No Known Activations