© 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. 15-LLAMASCOPE-RES-131K
    6. 27119
    Prev
    Next
    INDEX
    Explanations

    expressions related to professional expertise

    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
     Guess
    -0.07
    GLOSS
    -0.07
    Guess
    -0.06
     noisy
    -0.06
    burger
    -0.06
    èĥ¶
    -0.06
     duplic
    -0.06
    /goto
    -0.06
    .MockMvc
    -0.06
    à¸Ļà¸Ķ
    -0.06
    POSITIVE LOGITS
    į°
    0.07
    lip
    0.07
    ÙĩÙĨ
    0.07
    ãģıãģł
    0.07
     Sad
    0.06
    oard
    0.06
     sad
    0.06
    stral
    0.06
    inta
    0.06
    erece
    0.06
    Activations Density 0.024%

    No Known Activations