© 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. 60962
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consensus or agreement

    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
     phrase
    -0.06
    ERA
    -0.06
    afari
    -0.06
     grains
    -0.06
     word
    -0.06
    orris
    -0.05
    olith
    -0.05
     revealed
    -0.05
    ystick
    -0.05
    dux
    -0.05
    POSITIVE LOGITS
    ÏĮÏĦε
    0.07
    é³´
    0.07
    aight
    0.07
    _past
    0.07
    é
    0.07
    λεÏħ
    0.07
    νÏİ
    0.07
    _cached
    0.07
    xDD
    0.07
    LabelText
    0.07
    Activations Density 0.001%

    No Known Activations