© 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. 78061
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or presence

    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
     Blades
    -0.07
     Blade
    -0.06
    antro
    -0.06
    lub
    -0.06
     Tro
    -0.06
     Fog
    -0.06
    ouro
    -0.06
    opp
    -0.06
     anything
    -0.06
    ɵ
    -0.06
    POSITIVE LOGITS
    ima
    0.07
    ει
    0.07
    pair
    0.07
    ød
    0.07
    ’ta
    0.07
     actionTypes
    0.06
    igu
    0.06
     ActionTypes
    0.06
    amer
    0.06
    erton
    0.06
    Activations Density 0.033%

    No Known Activations