Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3600
    Prev
    Next
    INDEX
    Explanations

    technical terms related to design efficiency and functionality

    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
    olon
    -0.07
    Assignable
    -0.07
    κÏĮ
    -0.06
    äh
    -0.06
    CRET
    -0.06
    erra
    -0.06
    ERSHEY
    -0.06
    leta
    -0.06
     MyBase
    -0.06
    ãģ£ãģı
    -0.05
    POSITIVE LOGITS
    zel
    0.07
    ableView
    0.07
    eration
    0.07
    .Unicode
    0.07
     Exped
    0.06
     風
    0.06
    ãĤ¹ãĤ«
    0.06
     sight
    0.06
    UIView
    0.06
     Crush
    0.06
    Activations Density 0.046%

    No Known Activations