© 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. 40704
    Prev
    Next
    INDEX
    Explanations

    references to charitable donations and scams

    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
    oyal
    -0.07
    jeme
    -0.07
    lett
    -0.07
    ByExample
    -0.07
    vida
    -0.07
    agos
    -0.07
    era
    -0.07
    زد
    -0.07
    éĺ
    -0.06
    PickerController
    -0.06
    POSITIVE LOGITS
     sudden
    0.09
     suddenly
    0.08
     any
    0.07
     suspicious
    0.07
     anything
    0.06
    udden
    0.06
     unless
    0.06
    à¹ĥà¸Ķ
    0.06
    wart
    0.06
    ä»»ä½ķ
    0.06
    Activations Density 0.005%

    No Known Activations