© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78114
    Prev
    Next
    INDEX
    Explanations

    elements related to structural design and legal terminology

    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
    kla
    -0.06
    typ
    -0.06
    150
    -0.06
    pra
    -0.06
    EGIN
    -0.06
    enk
    -0.06
    ennes
    -0.06
    102
    -0.05
    iness
    -0.05
    la
    -0.05
    POSITIVE LOGITS
    à¹ģà¸ķ
    0.08
    dar
    0.08
    Margins
    0.07
    Dé
    0.07
    ToFit
    0.07
    ãĥĨãĥ«
    0.07
    주ìĭľ
    0.07
    主義
    0.07
    orno
    0.07
    ynchronously
    0.07
    Activations Density 0.064%

    No Known Activations