© 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. 17-LLAMASCOPE-RES-131K
    6. 93731
    Prev
    Next
    INDEX
    Explanations

    terms related to gambling and gaming

    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
    elman
    -0.07
    edor
    -0.07
    KN
    -0.06
    ISH
    -0.06
    opr
    -0.06
    uv
    -0.06
    ìĥģìĿĺ
    -0.06
    odie
    -0.06
     tvor
    -0.06
    çIJ´
    -0.06
    POSITIVE LOGITS
     tion
    0.08
     />
    0.07
     href
    0.07
    mouseleave
    0.07
    ldkf
    0.07
    .ud
    0.07
    ãĥ³ãĥĶ
    0.06
    ]={↵
    0.06
    _subplot
    0.06
    bstract
    0.06
    Activations Density 0.006%

    No Known Activations