© 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. 61921
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with political entities or references

    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
    atars
    -0.06
     opposite
    -0.06
     job
    -0.06
    rightness
    -0.05
     Canary
    -0.05
    aggio
    -0.05
    /job
    -0.05
    anking
    -0.05
    âĢ¦
    -0.05
     d
    -0.05
    POSITIVE LOGITS
     podrob
    0.07
    omen
    0.07
    bÃŃr
    0.07
     poil
    0.07
    ικα
    0.07
     جÙĦ
    0.07
    ÐłÐĺ
    0.06
    Hall
    0.06
    raphics
    0.06
    owitz
    0.06
    Activations Density 0.000%

    No Known Activations