© 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. 15-LLAMASCOPE-RES-131K
    6. 61781
    Prev
    Next
    INDEX
    Explanations

    references to human rights and legal frameworks

    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
    coop
    -0.07
    ONA
    -0.07
    orial
    -0.07
    lası
    -0.06
     gep
    -0.06
    eam
    -0.06
     addCriterion
    -0.06
     Flem
    -0.06
    itag
    -0.06
    atching
    -0.06
    POSITIVE LOGITS
     Human
    0.08
     human
    0.08
     UN
    0.07
    аÑĤков
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    eshire
    0.07
    ¦¬
    0.07
    Human
    0.07
     Sierra
    0.07
    strand
    0.07
    Activations Density 0.012%

    No Known Activations