© 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. 40080
    Prev
    Next
    INDEX
    Explanations

    events related to tradition and community activities

    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
     recently
    -0.06
     will
    -0.06
     tomorrow
    -0.05
    haf
    -0.05
    alem
    -0.05
    fullscreen
    -0.05
    ately
    -0.05
     lately
    -0.05
     tissue
    -0.05
     cor
    -0.05
    POSITIVE LOGITS
    inda
    0.08
     Antar
    0.08
    lub
    0.08
    porno
    0.08
    egin
    0.07
    rips
    0.07
    omik
    0.07
     напÑĢи
    0.07
    ãĤ¯ãĥ©ãĥĸ
    0.07
    tor
    0.07
    Activations Density 0.000%

    No Known Activations