© 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. 84042
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and operations involving output and state management

    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
    atz
    -0.08
    aid
    -0.06
     ATP
    -0.06
    ar
    -0.06
    åł´
    -0.05
     Tribute
    -0.05
     ode
    -0.05
     tribute
    -0.05
     (“
    -0.05
     Guidance
    -0.05
    POSITIVE LOGITS
    anela
    0.07
    .generated
    0.07
    eler
    0.07
    ört
    0.07
     ///<
    0.07
    bru
    0.07
    ãĤ¿ãĥ¼
    0.07
    PAIR
    0.07
    inz
    0.07
    .dep
    0.07
    Activations Density 0.028%

    No Known Activations