© 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. 17-LLAMASCOPE-RES-131K
    11. 86210
    Prev
    Next
    INDEX
    Explanations

    instances of corporate influence and manipulation of the internet

    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
    ηÏĤ
    -0.07
    peq
    -0.06
    izzo
    -0.06
     شع
    -0.06
     Dipl
    -0.06
    çľģ
    -0.06
    umber
    -0.06
     torment
    -0.06
    pga
    -0.06
    OCR
    -0.06
    POSITIVE LOGITS
    olin
    0.07
    olle
    0.07
     lock
    0.07
     locked
    0.07
    ÑĪев
    0.06
     locking
    0.06
    rent
    0.06
    ار
    0.06
    -commercial
    0.06
    atten
    0.06
    Activations Density 0.007%

    No Known Activations