© 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. 9-LLAMASCOPE-RES-131K
    11. 95604
    Prev
    Next
    INDEX
    Explanations

    phrases related to risk factors and their quantification

    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
    γη
    -0.08
    aze
    -0.08
    maz
    -0.08
    entine
    -0.07
    æļĹ
    -0.07
     Resolver
    -0.07
    oga
    -0.07
    utherland
    -0.07
    folk
    -0.07
    orrent
    -0.07
    POSITIVE LOGITS
    ³
    0.06
    ur
    0.06
     çĥ
    0.05
    zimmer
    0.05
    LER
    0.05
     Citizenship
    0.05
     Ellis
    0.05
    ì§ģ
    0.05
    792
    0.05
    osten
    0.05
    Activations Density 0.007%

    No Known Activations