© 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. 5-LLAMASCOPE-RES-131K
    11. 126470
    Prev
    Next
    INDEX
    Explanations

    phrases that describe mental or emotional states

    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
    FromClass
    -0.08
    ettle
    -0.08
    okane
    -0.07
    vatel
    -0.07
    ACA
    -0.07
    .fhir
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    hsi
    -0.07
    úb
    -0.07
    ableOpacity
    -0.07
    POSITIVE LOGITS
    oss
    0.07
    wr
    0.07
     uns
    0.06
     wr
    0.06
     Pang
    0.06
    anter
    0.05
     lev
    0.05
    ipline
    0.05
    aron
    0.05
     Lev
    0.05
    Activations Density 0.003%

    No Known Activations