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. 5308
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tag structures

    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
    673
    -0.07
    çĶ
    -0.06
     phục
    -0.06
    renom
    -0.06
    aha
    -0.06
    ugu
    -0.06
    segments
    -0.06
    oop
    -0.06
    typing
    -0.06
    .aspx
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    antas
    0.07
    alth
    0.07
    uteur
    0.07
    #
    0.07
    .infinity
    0.07
    evenodd
    0.07
    ê±°ëŀĺê°Ģ
    0.07
    291
    0.06
     èĹ
    0.06
    Activations Density 0.006%

    No Known Activations