© 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. 89158
    Prev
    Next
    INDEX
    Explanations

    contrasting descriptions evaluating the qualities of various subjects, particularly in artistic or creative contexts

    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
    lok
    -0.06
    icast
    -0.06
    ãĥĢãĥ¼
    -0.06
    urger
    -0.06
     Gran
    -0.06
    ined
    -0.05
    luck
    -0.05
    URT
    -0.05
     switches
    -0.05
     “
    -0.05
    POSITIVE LOGITS
    åį´
    0.07
    èĻŁ
    0.07
     suf
    0.07
    cket
    0.07
     complexity
    0.07
    _COMP
    0.07
     Complexity
    0.07
     Barcl
    0.07
    elo
    0.07
    å¤į
    0.07
    Activations Density 0.033%

    No Known Activations