© 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 EvalsExportsinterp-engineNEWAPI 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. 124393
    Prev
    Next
    INDEX
    Explanations

    mentions of collaborations or features involving artists and their works

    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
    oser
    -0.09
    Tại
    -0.08
    erap
    -0.08
    ellan
    -0.08
    resher
    -0.08
    lop
    -0.08
    ayne
    -0.08
     kred
    -0.08
    елеÑĦ
    -0.07
    deaux
    -0.07
    POSITIVE LOGITS
     former
    0.14
     Former
    0.10
    former
    0.10
    0.09
    Former
    0.08
     star
    0.08
     world
    0.07
     icon
    0.07
     known
    0.07
     triple
    0.07
    Activations Density 0.085%

    No Known Activations