© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127750
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to entities, primarily in legal, business, and creative 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
    zw
    -0.07
    461
    -0.06
     scenario
    -0.06
     fi
    -0.06
    chi
    -0.06
    IAS
    -0.05
    329
    -0.05
    AS
    -0.05
    307
    -0.05
    kl
    -0.05
    POSITIVE LOGITS
     whose
    0.12
    whose
    0.09
     ÏĢοÏħ
    0.09
    ople
    0.08
     коÑĤоÑĢÑĭй
    0.08
     mÃł
    0.07
    upal
    0.07
     ÙĥÙĩ
    0.07
    кÑĢеÑĤ
    0.07
     who
    0.07
    Activations Density 0.037%

    No Known Activations