© 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. 5-LLAMASCOPE-RES-131K
    11. 125464
    Prev
    Next
    INDEX
    Explanations

    terms related to mystery or enigmatic elements

    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
    YSTEM
    -0.07
    serter
    -0.07
    IFn
    -0.06
     maduras
    -0.06
    μι
    -0.06
    еÑĢж
    -0.06
    -host
    -0.06
    rouch
    -0.06
    CallCheck
    -0.06
    ACHE
    -0.06
    POSITIVE LOGITS
    ocker
    0.08
     Hindered
    0.07
    abant
    0.07
    gings
    0.07
    çª
    0.06
    omen
    0.06
    rzy
    0.06
     ag
    0.06
    quot
    0.06
    /vue
    0.06
    Activations Density 0.000%

    No Known Activations