© 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. 57073
    Prev
    Next
    INDEX
    Explanations

    specific conditions or requirements related to different subjects or processes

    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
    eri
    -0.06
    715
    -0.06
     Specialty
    -0.06
    λÏĮ
    -0.06
    691
    -0.06
    fully
    -0.06
    åIJ§
    -0.06
    tae
    -0.06
    olem
    -0.06
    epar
    -0.06
    POSITIVE LOGITS
     certain
    0.28
     Certain
    0.23
    æŁIJ
    0.21
    Certain
    0.21
     particular
    0.21
     bestimm
    0.19
     certains
    0.17
     specific
    0.16
    ertain
    0.14
     belirli
    0.14
    Activations Density 0.081%

    No Known Activations