© 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. 85235
    Prev
    Next
    INDEX
    Explanations

    issues related to systemic challenges and their impacts on governance

    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
    plete
    -0.07
    769
    -0.06
    regor
    -0.06
    AppComponent
    -0.06
    icom
    -0.06
    phia
    -0.06
     localVar
    -0.06
    orr
    -0.06
    (strpos
    -0.06
    aram
    -0.06
    POSITIVE LOGITS
     obstacle
    0.09
     obstacles
    0.08
     imped
    0.08
     ham
    0.07
    bars
    0.07
     cloud
    0.07
     hind
    0.07
     barriers
    0.07
     limit
    0.06
    chet
    0.06
    Activations Density 0.073%

    No Known Activations