© 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. 15-LLAMASCOPE-RES-131K
    11. 89089
    Prev
    Next
    INDEX
    Explanations

    references to authenticity or the concept of being real

    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
    eling
    -0.08
    esh
    -0.08
    esch
    -0.08
    ess
    -0.07
    etik
    -0.07
    edi
    -0.07
    esi
    -0.07
    eding
    -0.06
    ese
    -0.06
    kor
    -0.06
    POSITIVE LOGITS
    mente
    0.15
    ity
    0.13
    ités
    0.12
    ities
    0.11
    istically
    0.10
    ignment
    0.10
    dehyde
    0.10
    itate
    0.10
    ized
    0.09
    ITY
    0.09
    Activations Density 0.014%

    No Known Activations