© 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. 74690
    Prev
    Next
    INDEX
    Explanations

    legislative proposals and their intended outcomes

    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
     geh
    -0.06
    wich
    -0.06
     Kür
    -0.06
     tariffs
    -0.06
    /auto
    -0.06
     Initialise
    -0.06
    ussen
    -0.06
    ì§
    -0.06
    /--
    -0.06
    /twitter
    -0.05
    POSITIVE LOGITS
    vais
    0.09
    igkeit
    0.08
     CONSEQUENTIAL
    0.07
     Allow
    0.07
    oga
    0.07
    idal
    0.07
    ozem
    0.07
    toi
    0.07
    оиÑĤ
    0.07
    unk
    0.06
    Activations Density 0.013%

    No Known Activations