© 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. 126811
    Prev
    Next
    INDEX
    Explanations

    references to voting processes and political decision-making

    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
    Locator
    -0.07
    ÙĥÙĬÙĦ
    -0.06
    anan
    -0.06
    emento
    -0.06
    .NORTH
    -0.06
    ogn
    -0.06
    /compiler
    -0.06
    å½
    -0.06
    áli
    -0.06
    _HELPER
    -0.06
    POSITIVE LOGITS
     once
    0.18
    once
    0.17
    Once
    0.15
     Once
    0.15
     subsequent
    0.14
     afterwards
    0.14
     after
    0.13
     thereafter
    0.12
     subsequently
    0.12
     post
    0.11
    Activations Density 0.144%

    No Known Activations