© 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. 785
    Prev
    Next
    INDEX
    Explanations

    references to educational and training activities

    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
    lesc
    -0.07
    olu
    -0.06
    ekk
    -0.06
    atalog
    -0.06
    itional
    -0.06
    मà¤ķ
    -0.06
    autos
    -0.06
    eca
    -0.06
    cord
    -0.06
    ach
    -0.05
    POSITIVE LOGITS
    reh
    0.08
     modern
    0.07
    ,eg
    0.07
    :Event
    0.07
     newer
    0.06
     learning
    0.06
    inton
    0.06
     बद
    0.06
     frequent
    0.06
     cutting
    0.06
    Activations Density 0.017%

    No Known Activations