© 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. 61252
    Prev
    Next
    INDEX
    Explanations

    references to addiction and its consequences

    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
    ê·
    -0.07
    odu
    -0.07
    lluminate
    -0.06
    omu
    -0.06
    pecia
    -0.06
    zek
    -0.06
    ronym
    -0.06
    .Sync
    -0.06
    isors
    -0.06
    esy
    -0.06
    POSITIVE LOGITS
     reward
    0.10
     addictive
    0.10
     dopamine
    0.08
     pleasure
    0.08
    reward
    0.08
     Pav
    0.08
     addiction
    0.08
     addict
    0.08
     Reward
    0.08
     rewards
    0.08
    Activations Density 0.008%

    No Known Activations