© 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. 28716
    Prev
    Next
    INDEX
    Explanations

    terms related to roller coasters and amusement park rides

    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
    orial
    -0.07
    ãĥ¼ãĥī
    -0.07
    soever
    -0.07
    irs
    -0.07
    visor
    -0.07
    üçük
    -0.07
    flows
    -0.07
    space
    -0.07
     Rot
    -0.06
    .GetEnumerator
    -0.06
    POSITIVE LOGITS
     ride
    0.10
    roller
    0.08
     rides
    0.07
     Ride
    0.07
    LIK
    0.06
    lik
    0.06
    itis
    0.06
    etty
    0.06
    utta
    0.06
     roller
    0.06
    Activations Density 0.003%

    No Known Activations