Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43507
    Prev
    Next
    INDEX
    Explanations

    concepts related to addiction recovery and the support systems involved

    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
    polator
    -0.07
     pestic
    -0.07
     dilig
    -0.07
    ÐŁÐļ
    -0.06
    omik
    -0.06
    μοÏħ
    -0.06
    .oracle
    -0.06
    .emf
    -0.06
     vect
    -0.06
    èĪª
    -0.06
    POSITIVE LOGITS
     rehab
    0.18
     Rehab
    0.17
     Alcohol
    0.17
     alcohol
    0.16
     rehabilitation
    0.15
     Addiction
    0.15
     addiction
    0.14
     Rehabilitation
    0.14
     rehabilit
    0.14
     detox
    0.14
    Activations Density 0.011%

    No Known Activations