© 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. 15-LLAMASCOPE-RES-131K
    11. 61360
    Prev
    Next
    INDEX
    Explanations

    elements related to web addresses or URLs

    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
     Cheers
    -0.06
     primes
    -0.06
     steering
    -0.06
     lamin
    -0.06
    018
    -0.05
    ouver
    -0.05
    esModule
    -0.05
    \Core
    -0.05
     Main
    -0.05
    è
    -0.05
    POSITIVE LOGITS
    ланд
    0.08
    dent
    0.07
    atte
    0.07
    ollapsed
    0.07
     vÃŃde
    0.07
    mobx
    0.07
    çĨ
    0.06
    bidden
    0.06
    deo
    0.06
     Tek
    0.06
    Activations Density 0.001%

    No Known Activations