© 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. 55831
    Prev
    Next
    INDEX
    Explanations

    creative content and media-related terms

    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
     batt
    -0.06
     hem
    -0.06
    aho
    -0.06
    hap
    -0.05
    /entities
    -0.05
    åħĪçĶŁ
    -0.05
    æļ´
    -0.05
    VEL
    -0.05
     partida
    -0.05
    174
    -0.05
    POSITIVE LOGITS
    αιν
    0.08
    _unregister
    0.08
    odb
    0.07
    ForMember
    0.07
    oga
    0.07
    unlink
    0.07
    ãĥ³ãĥĦ
    0.07
     Sesso
    0.07
    incy
    0.06
    ogui
    0.06
    Activations Density 0.046%

    No Known Activations