© 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. 103898
    Prev
    Next
    INDEX
    Explanations

    phrases that question actions and intentions

    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
    ÑĮко
    -0.06
    êm
    -0.06
    uky
    -0.06
     gost
    -0.06
    ains
    -0.06
    bor
    -0.06
     pi
    -0.06
    бин
    -0.06
    enn
    -0.06
    rate
    -0.06
    POSITIVE LOGITS
     nor
    0.25
     Nor
    0.20
    nor
    0.19
     neither
    0.18
    Nor
    0.18
     Neither
    0.15
     NOR
    0.14
    Neither
    0.12
    ä¹Łä¸į
    0.11
     sondern
    0.10
    Activations Density 0.143%

    No Known Activations