© 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. 126966
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant consequence or criminal act

    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
    oten
    -0.07
    ,
    -0.06
     âĢİ
    -0.06
    âĢİ
    -0.06
     lesser
    -0.06
    alc
    -0.06
    977
    -0.06
    积
    -0.05
     similarly
    -0.05
    .git
    -0.05
    POSITIVE LOGITS
    OffsetTable
    0.09
    .WinForms
    0.08
    	and
    0.08
    SError
    0.08
    ande
    0.07
    GenerationStrategy
    0.07
    iasi
    0.07
    amina
    0.07
    istrovstvÃŃ
    0.07
     and
    0.07
    Activations Density 0.030%

    No Known Activations