© 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. 61383
    Prev
    Next
    INDEX
    Explanations

    technical problems or failures in processes or systems

    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
     scarc
    -0.07
    abr
    -0.07
    kop
    -0.06
    hta
    -0.06
    bole
    -0.06
    FI
    -0.06
    @student
    -0.06
    otten
    -0.06
    achu
    -0.06
    igure
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.10
     after
    0.07
    DEX
    0.07
     weird
    0.07
    after
    0.06
     Weird
    0.06
    оÑĢд
    0.06
    лки
    0.06
     lately
    0.06
     ÑĥÑĩаÑģÑĤи
    0.06
    Activations Density 0.012%

    No Known Activations