© 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. 16623
    Prev
    Next
    INDEX
    Explanations

    specific references to political figures and 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
     Gon
    -0.07
    873
    -0.07
    roup
    -0.07
     suck
    -0.06
    asu
    -0.06
    çĵľ
    -0.06
     thunk
    -0.06
    ctica
    -0.06
     Hund
    -0.06
    اÙĩد
    -0.06
    POSITIVE LOGITS
    åºķ
    0.07
    edList
    0.06
    uding
    0.06
    mac
    0.06
    opens
    0.06
    adar
    0.06
    leet
    0.06
    macros
    0.06
     CRS
    0.06
    adelphia
    0.06
    Activations Density 0.390%

    No Known Activations