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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4855
    Prev
    Next
    INDEX
    Explanations

    terms and discussions related to digital rights and legal issues in the arts

    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
    Ùıس
    -0.07
    loff
    -0.07
     Loans
    -0.06
    wald
    -0.06
    ysl
    -0.06
    cona
    -0.06
     commute
    -0.06
     Sle
    -0.06
    REFER
    -0.06
    à¸Ńม
    -0.06
    POSITIVE LOGITS
     sublic
    0.13
     sublicense
    0.11
     licensing
    0.11
     license
    0.10
     royalty
    0.09
     rights
    0.09
     licenses
    0.09
     licence
    0.09
     License
    0.09
    -License
    0.09
    Activations Density 0.018%

    No Known Activations