© 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. 17-LLAMASCOPE-RES-131K
    11. 106339
    Prev
    Next
    INDEX
    Explanations

    references to corruption and financial misconduct

    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
     Due
    -0.06
    Dev
    -0.06
    .createFrom
    -0.06
     smo
    -0.06
     seper
    -0.06
     whilst
    -0.06
    ise
    -0.06
    Due
    -0.05
    ħĮ
    -0.05
    éħ
    -0.05
    POSITIVE LOGITS
     meanwhile
    0.08
    ebi
    0.07
    _que
    0.07
    oka
    0.07
    /WebAPI
    0.07
    itom
    0.06
     dozens
    0.06
     ÑĤоÑĢ
    0.06
     ваÑĢианÑĤ
    0.06
     moreover
    0.06
    Activations Density 0.163%

    No Known Activations