© 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. 119399
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals in an academic or professional context

    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
    ãģ
    -0.07
    athi
    -0.07
    hoe
    -0.06
     offsetof
    -0.06
    _linux
    -0.06
    adian
    -0.06
    .tt
    -0.06
    å¹³æĪIJ
    -0.06
    è³¢
    -0.06
    atura
    -0.06
    POSITIVE LOGITS
     Department
    0.07
    ptal
    0.07
    ulos
    0.07
    Department
    0.07
    osi
    0.07
    dept
    0.07
    rias
    0.07
    OPSIS
    0.06
    University
    0.06
     rais
    0.06
    Activations Density 0.051%

    No Known Activations