© 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. 62163
    Prev
    Next
    INDEX
    Explanations

    references to lottery scams and related fraudulent activities

    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
    unger
    -0.07
    unch
    -0.07
    pk
    -0.07
    boru
    -0.06
    lett
    -0.06
    bourg
    -0.06
    ÙĪزÛĮ
    -0.06
    chet
    -0.06
    ouri
    -0.06
    nemonic
    -0.06
    POSITIVE LOGITS
    sss
    0.07
     ActionTypes
    0.06
     Eag
    0.06
     Pond
    0.06
     Baxter
    0.06
    lim
    0.06
    ActionTypes
    0.06
     ciz
    0.06
    validate
    0.06
     ph
    0.05
    Activations Density 0.005%

    No Known Activations