© 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. 17-LLAMASCOPE-RES-131K
    6. 93980
    Prev
    Next
    INDEX
    Explanations

    citations and metadata related to academic articles

    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
    388
    -0.06
    376
    -0.06
    468
    -0.06
    urum
    -0.06
     Downs
    -0.06
     quot
    -0.06
    éīĦ
    -0.06
     ex
    -0.05
     ÐĿаз
    -0.05
    AFE
    -0.05
    POSITIVE LOGITS
    Ú¯ÛĮر
    0.07
    ân
    0.07
     shape
    0.07
    آخر
    0.07
     edits
    0.07
     vandalism
    0.07
    .wik
    0.07
    ioni
    0.07
     vandal
    0.07
    endid
    0.07
    Activations Density 0.003%

    No Known Activations