© 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. 76933
    Prev
    Next
    INDEX
    Explanations

    features related to amusement park attractions

    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
    444
    -0.06
    634
    -0.06
     Morse
    -0.06
    igr
    -0.06
    161
    -0.06
    842
    -0.06
     Moral
    -0.05
    673
    -0.05
     anchored
    -0.05
     walks
    -0.05
    POSITIVE LOGITS
    namen
    0.08
    eya
    0.07
    repid
    0.07
     Riders
    0.07
    andas
    0.07
     riders
    0.07
    çĢ¬
    0.07
    antu
    0.07
    лиÑĨ
    0.07
     Wrapper
    0.07
    Activations Density 0.004%

    No Known Activations