© 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. 15-LLAMASCOPE-RES-131K
    11. 1078
    Prev
    Next
    INDEX
    Explanations

    mentions of purchasing medications online

    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
     Certif
    -0.07
    hsi
    -0.07
    bery
    -0.07
    kova
    -0.07
    edl
    -0.06
    grunt
    -0.06
    .dtype
    -0.06
    eft
    -0.06
    openh
    -0.06
    ritz
    -0.06
    POSITIVE LOGITS
    zen
    0.07
    oder
    0.06
    MEM
    0.06
     UK
    0.06
    anst
    0.06
    APON
    0.06
    lrt
    0.06
    714
    0.06
    IME
    0.06
    edy
    0.06
    Activations Density 0.003%

    No Known Activations