© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125950
    Prev
    Next
    INDEX
    Explanations

    discussions of proposals or recommendations, particularly regarding health regulations

    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
    atra
    -0.07
    ream
    -0.07
    NEXT
    -0.06
    FragmentManager
    -0.05
    811
    -0.05
    olate
    -0.05
    imo
    -0.05
    ucas
    -0.05
    ou
    -0.05
     Rao
    -0.05
    POSITIVE LOGITS
     previous
    0.30
     earlier
    0.24
    previous
    0.24
     Previous
    0.23
    Previous
    0.22
     previously
    0.21
    (previous
    0.19
    .previous
    0.19
     Previously
    0.18
    _previous
    0.18
    Activations Density 0.239%

    No Known Activations