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

    Neuronpedia

    Jacobian LensNEW
    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. 130801
    Prev
    Next
    INDEX
    Explanations

    phrases related to attention and observation

    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
    èħ
    -0.07
    OKEN
    -0.07
    odge
    -0.07
    IMO
    -0.07
    unts
    -0.07
    quoi
    -0.06
    ामन
    -0.06
    okens
    -0.06
    stants
    -0.06
    odore
    -0.06
    POSITIVE LOGITS
     Co
    0.06
    ä¸Ģä¸ĭ
    0.06
    waves
    0.06
    寧
    0.06
    ingly
    0.06
    apis
    0.06
    coder
    0.06
     more
    0.06
     Cooper
    0.05
    ucid
    0.05
    Activations Density 0.007%

    No Known Activations