© 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. 16334
    Prev
    Next
    INDEX
    Explanations

    references to tax topics and related financial matters

    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
    iae
    -0.09
    anse
    -0.08
    ibs
    -0.08
    halt
    -0.07
    ầu
    -0.07
    ãĥ¡ãĥ³ãĥĪ
    -0.07
    orde
    -0.07
    íĴĪ
    -0.07
    '=>"
    -0.07
    ispecies
    -0.07
    POSITIVE LOGITS
    alog
    0.06
    onomic
    0.06
    lor
    0.06
    -related
    0.06
     arbit
    0.06
     giant
    0.06
    zin
    0.06
     treatment
    0.06
    ym
    0.06
    afort
    0.06
    Activations Density 0.011%

    No Known Activations