© 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. 61372
    Prev
    Next
    INDEX
    Explanations

    concepts related to health, economic conditions, and community impact

    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
    acific
    -0.07
    uge
    -0.06
    ilig
    -0.06
    .cn
    -0.06
    immel
    -0.06
    Ø·Ùģ
    -0.06
    assen
    -0.06
    еÑī
    -0.06
    Çİ
    -0.06
    INO
    -0.06
    POSITIVE LOGITS
     thereby
    0.13
     hence
    0.13
    thus
    0.12
     thus
    0.12
     therefore
    0.09
     which
    0.09
     Hence
    0.09
     enough
    0.08
     donc
    0.08
     and
    0.08
    Activations Density 0.109%

    No Known Activations