© 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. 78592
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to regulations and licensing

    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
     âĢIJ
    -0.08
     ÑģÑĤаÑĢа
    -0.07
    NewLabel
    -0.07
     ÑıкоÑģÑĤÑĸ
    -0.07
    InputDialog
    -0.07
    .Restrict
    -0.07
     минÑĥ
    -0.07
    æĿī
    -0.07
    arpa
    -0.06
    анов
    -0.06
    POSITIVE LOGITS
     "
    0.18
     «
    0.17
     '
    0.15
     “
    0.12
    ="
    0.12
     `
    0.12
    ãĢĮ
    0.12
     \"
    0.12
    ("
    0.11
     ``
    0.10
    Activations Density 0.144%

    No Known Activations