© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90189
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and protections concerning controlled substances

    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
    204
    -0.07
    us
    -0.06
    elf
    -0.06
    vak
    -0.06
    æ½®
    -0.05
    inet
    -0.05
    NO
    -0.05
    ourt
    -0.05
    oda
    -0.05
    824
    -0.05
    POSITIVE LOGITS
    ãĥĥãĥĦ
    0.09
    edList
    0.09
    AndView
    0.09
    /non
    0.08
    elper
    0.08
    izable
    0.08
    edImage
    0.08
    -status
    0.08
    leted
    0.07
    eniable
    0.07
    Activations Density 0.015%

    No Known Activations