© 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. 85381
    Prev
    Next
    INDEX
    Explanations

    elements related to pop culture and entertainment reviews

    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
    izu
    -0.07
    iare
    -0.06
    chos
    -0.06
    ramids
    -0.06
    erah
    -0.06
    ç·Ĵ
    -0.06
    arnation
    -0.06
     Serialization
    -0.06
    ragon
    -0.06
    entiful
    -0.06
    POSITIVE LOGITS
     unofficial
    0.07
     recreation
    0.06
    eder
    0.06
     коÑĢиÑģÑĤ
    0.06
    ä¼ģ
    0.06
     reinterpret
    0.06
    Parms
    0.06
     تض
    0.06
    .mock
    0.06
    æ®
    0.06
    Activations Density 0.022%

    No Known Activations