© 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. 57503
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to image enlargement and visual scales

    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
    merce
    -0.07
    ala
    -0.07
    нима
    -0.06
    lessly
    -0.06
    rary
    -0.06
    icz
    -0.06
    ãĥķãĤ§
    -0.06
    RAIN
    -0.06
    ики
    -0.06
    Ïģιά
    -0.06
    POSITIVE LOGITS
    usp
    0.07
     Lever
    0.07
    eve
    0.07
    idia
    0.07
    able
    0.06
    abin
    0.06
    712
    0.06
    -lnd
    0.06
    ToFit
    0.06
    maal
    0.06
    Activations Density 0.004%

    No Known Activations