© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40789
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or positive interest

    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
    anson
    -0.08
    adge
    -0.07
    æ³£
    -0.07
    ugin
    -0.07
    podob
    -0.07
    eper
    -0.07
    arro
    -0.06
    eren
    -0.06
    brahim
    -0.06
    arian
    -0.06
    POSITIVE LOGITS
    atically
    0.07
    pretty
    0.07
    igne
    0.06
     towards
    0.06
    nel
    0.06
     toward
    0.06
     quot
    0.06
    warts
    0.06
    )prepare
    0.06
     Pretty
    0.06
    Activations Density 0.007%

    No Known Activations