© 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. 22-LLAMASCOPE-RES-131K
    6. 4322
    Prev
    Next
    INDEX
    Explanations

    concepts related to problems, issues, and questions in various contexts

    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
    theless
    -0.08
    utterstock
    -0.07
    /exec
    -0.07
    vit
    -0.07
    ãģijãĤĮãģ°
    -0.07
    è¿Ļæł·çļĦ
    -0.07
    ulması
    -0.06
    composed
    -0.06
    akin
    -0.06
    FromClass
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.10
    /question
    0.08
    /framework
    0.06
    NING
    0.06
    791
    0.06
    oins
    0.06
    /problem
    0.06
    oid
    0.06
    år
    0.06
    363
    0.06
    Activations Density 0.086%

    No Known Activations