© 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. 129559
    Prev
    Next
    INDEX
    Explanations

    terms related to media or format specifications

    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
    wins
    -0.08
    ÂŃi
    -0.07
    isper
    -0.07
    tring
    -0.07
    ìĥĿ
    -0.07
    ر
    -0.07
    nings
    -0.07
    ż
    -0.07
    ogenous
    -0.06
    ÙĨاÙĨ
    -0.06
    POSITIVE LOGITS
    entimes
    0.07
    eson
    0.07
    site
    0.07
    ake
    0.07
    اء
    0.07
    sy
    0.07
    ertia
    0.07
    aken
    0.06
    uck
    0.06
    wich
    0.06
    Activations Density 0.026%

    No Known Activations