© 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. 9-LLAMASCOPE-RES-131K
    11. 96538
    Prev
    Next
    INDEX
    Explanations

    mentions of political entities or endorsements

    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
    rů
    -0.07
     âĹİ
    -0.07
    ether
    -0.07
     Parkinson
    -0.06
    abı
    -0.06
    ÄĻk
    -0.06
    кам
    -0.06
    iasi
    -0.06
    inel
    -0.06
    repos
    -0.06
    POSITIVE LOGITS
    377
    0.07
    q
    0.06
    aco
    0.06
    hall
    0.06
     ham
    0.06
     Gest
    0.05
    $
    0.05
    ContentType
    0.05
     tribute
    0.05
    DD
    0.05
    Activations Density 0.039%

    No Known Activations