© 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. 15-LLAMASCOPE-RES-131K
    11. 103792
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences or testimonies related to distressing events

    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
    280
    -0.06
    ates
    -0.06
     Ok
    -0.06
     &
    -0.06
    esson
    -0.06
    ?
    -0.06
    iris
    -0.05
    fs
    -0.05
    arden
    -0.05
     âĢ¦
    -0.05
    POSITIVE LOGITS
    edor
    0.07
    ibase
    0.07
    PFN
    0.07
    åıĤ
    0.07
    ساÙĨÛĮ
    0.07
     Bilg
    0.07
    ýt
    0.07
    ลล
    0.07
    PILE
    0.07
    ÙĤد
    0.07
    Activations Density 0.000%

    No Known Activations