© 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. 90311
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and variations indicating location or involvement

    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
    enso
    -0.07
     Geg
    -0.07
    ansa
    -0.07
    JUnit
    -0.07
    corn
    -0.07
    ekim
    -0.06
    GMT
    -0.06
    ÙĦØŃ
    -0.06
    aways
    -0.06
     Jennings
    -0.06
    POSITIVE LOGITS
     which
    0.08
    which
    0.07
    iasco
    0.07
    ÂĢÂ
    0.06
     chez
    0.06
     ÙĪاÙĦتÙĬ
    0.06
    verts
    0.06
    .k
    0.06
     WHICH
    0.06
     itself
    0.06
    Activations Density 0.049%

    No Known Activations