© 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. 129211
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repeated positive experiences with services or products

    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
     unsustainable
    -0.06
    irit
    -0.06
    ÏĢον
    -0.06
    nic
    -0.06
    unter
    -0.06
     relentless
    -0.05
     Altern
    -0.05
     succ
    -0.05
    ustin
    -0.05
    hero
    -0.05
    POSITIVE LOGITS
     future
    0.09
     anytime
    0.09
    future
    0.09
    ToSelector
    0.08
     whenever
    0.08
    Interop
    0.08
    .future
    0.07
     бÑĥдÑĥÑī
    0.07
    GuidId
    0.07
    iglia
    0.07
    Activations Density 0.008%

    No Known Activations